Your search

Economic load dispatch (ELD) is a challenge optimization problem to minimize the total cost of the thermally generated power that satisfies a set of equality and inequality constraints. We need to maximize the power network load under several operational constraints to solve this problem. Meanwhile, we need to minimize the cost of power generation and minimize the loss in the network transmission. Traditional optimization methods were used to solve such problems as linear programming. Meta-heuristic search algorithms have shown encouraging performance in solving various real-life engineering problems. This paper attempts to provide a comprehensive comparison between nine meta-heuristic search algorithms, including Genetic Algorithms (GAs), Particle Swarm Optimization (PSO), Crow Search Algorithm (CSA), Differential Evolution (DE), Salp Swarm Algorithm (SSA), Harmony Search (HS), Sine Cosine Algorithm (SCA), Multi-Verse Optimizer (MVO), and Moth-Flame Optimization Algorithm (MFO) for solving the economic load dispatch problem. Our developed results demonstrated that meta-heuristics search algorithms (i.e., CSA and DE) offer the optimal power set for each power station. These computed power fulfill the supply needs and maintain both minimum power costs and power losses in power transmission.

We incorporate deep learning techniques into capacitive images of body parts (ear, four fingers, and thumb) to improve the performance of user authentication in smartphones. Use of a capacitive touchscreen as an image sensor has several advantages, such as it is less sensitive to poor illumination conditions, occlusions, and pose variations. Also, it does not need an additional hardware like iris or fingerprint scanner. Use of capacitive images for user authentication is not new. However, the performance, specially, false reject rates (FRRs) of the state-of-the-art capacitive image-based systems are poor. In this paper, we focus on improving the performance and leverage deep learning. Deep learning techniques demonstrated spectacular performance in previous physical biometrics-based research. However, to our knowledge, effectiveness of deep learning is still unexplored in capacitive touchscreen-based user authentication. In order to bridge this research gap, we devise a multi-modal deep learning model, namely UASNet, and compare its performance with a large set of uni- and multi-modal baselines. Using the UASNet, we achieve an accuracy of 99.77%, an EER of 0.48%, and an FRR of 1.19% at FAR of 0.06%.

Cardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on non-invasive methods such as retinal image or dual-energy X-ray absorptiometry (DXA). In this study, we aimed at diagnosing CVD using a novel approach integrating information from retinal images and DXA data. We considered an adult Qatari cohort of 500 participants from Qatar Biobank (QBB) with an equal number of participants from the CVD and the control groups. We designed a case-control study with a novel multi-modal (combining data from multiple modalities—DXA and retinal images)—to propose a deep learning (DL)-based technique to distinguish the CVD group from the control group. Uni-modal models based on retinal images and DXA data achieved 75.6% and 77.4% accuracy, respectively. The multi-modal model showed an improved accuracy of 78.3% in classifying CVD group and the control group. We used gradient class activation map (GradCAM) to highlight the areas of interest in the retinal images that influenced the decisions of the proposed DL model most. It was observed that the model focused mostly on the centre of the retinal images where signs of CVD such as hemorrhages were present. This indicates that our model can identify and make use of certain prognosis markers for hypertension and ischemic heart disease. From DXA data, we found higher values for bone mineral density, fat content, muscle mass and bone area across majority of the body parts in CVD group compared to the control group indicating better bone health in the Qatari CVD cohort. This seminal method based on DXA scans and retinal images demonstrate major potentials for the early detection of CVD in a fast and relatively non-invasive manner.

In the last decade, a wide range of machine learning approaches were proposed and experimented to model highly nonlinear manufacturing processes. However, improving the performance of such models is challenging due to the complexity and high dimensionality of the manufacturing processes in general. In this paper, we propose bidirectional echo state reservoir networks (Bi-ESNs) trained using support vector machine privileged information method (SVM$$+$$) to model a winding machine process. The proposed model will be applied, tested and compared to reported models in the literature such as classical ESN with linear regression, ESN with a linear SVM readout, genetic programming, feedfoward neural network with backpropagation, radial basis function network, adaptive neural fuzzy inference system and local linear wavelet neural network. The developed results show that Bi-ESNs trained with SVM$$+$$are promising. It was able to provide better generalization performance compared to other models.

In online social networks (OSN), followers count is a sign of the social influence of an account. Some users expect to increase the followers count by following more accounts. However, in reality more followings do not generate more followers. In this paper, we propose a two player follow-unfollow game model and then introduce a factor for promoting cooperation. Based on the two player follow-unfollow game, we create an evolutionary follow-unfollow game with more players to simulate a miniature social network. We design an algorithm and conduct the simulation. From the simulation, we find that our algorithm for the evolutionary follow-unfollow game is able to converge and produce a stable network. Results obtained with different values of the cooperation promotion factor show that the promotion factor increases the total connections in the network especially through increasing the number of the follow follow connections.

The Internet contains large amounts of adult content. With only a few taps, or mis-taps, an under-aged user can be exposed to age-inappropriate content. Currently, this can be avoided by creating age-restricted profiles or restricting users to child-friendly applications (apps). However, these existing measures are time-consuming, laborious, and require a higher level of technical literacy than many parents can afford. We believe a better solution is to use a browser or an app that automatically detects the user's age then applies any appropriate content filters. For such a browser/app to be developed, we must learn that age estimation can indeed be performed with an acceptable rate of error. To that end, we created an Android app that collects biometric touchscreen data from elementary school, middle school, high school, and university students. Touch samples were collected from participants aged 5 to 61 on both smartphones and tablets. We focused exclusively on zoom-in and zoom-out touchscreen data samples. We made this decision because we found the zoom gesture to be rich with data and highly used among the most popular applications. Furthermore, we identify a niche within the current research landscape: no other machine learning experiments have leveraged the benefits of the zoom gesture for age estimation. We collected a total of 41,911 zoom data samples. From each zoom sample, 90 features were extracted. Those features were then used to train and test on six regressors and six classifiers to build a method that can accurately estimate the user's age from their touchscreen behavior. The regressors performed with the best mean absolute errors (MAEs) of 2.27 and 2.54 years for smartphones and tablets, respectively. The classifiers performed with the best accuracies of 90% and 91% for smartphones and tablets, respectively. Given these results, it is our belief that not only is touch-based age estimation viable, but developing a child-safe browser or a parental control app with this underlying technology is a worthwhile endeavor. © 2022 Elsevier Ltd

Following Mandelbrot's fractal theory, it was found that the fractal dimension could be obtained in medical images by the concept of fractional Brownian motion. An estimation concept for determination of the fractal dimension based upon the concept of fractional Brownian motion was discussed. Two applications were found: 1) classification; 2) edge enhancement and detection. For the purpose of classification, a normalized fractional Brownian motion feature vector was defined from this estimation concept. It represented the normalized average absolute intensity difference of pixel pairs on a surface at different scales. The feature vector used relatively few data items to represent the statistical characteristics of the medical image surface and was invariant to linear intensity transformation. Finally, by calculating normalized fractional Brownian motion feature vectors in five different ultrasonic image surfaces, it was found that the classification of normal and abnormal ultrasonic liver images could be obtained from the differences between their feature vectors. For edge enhancement and detection application, a transformed image was obtained by calculating the fractal dimension of each pixel over the whole medical image. The fractal dimension value of each pixel was obtained by calculating the fractal dimension of a 7 x 7 pixel block centered on this pixel. Preliminary results using projection radiographs suggest that the fractal based image transformation appears to hold promise as an edge enhancement and preprocessing algorithm that does not increase noise in the way that gradient operators do. © 1989 IEEE

Qualitative analysis is important because it is not subjective and does not have the potential for variation from one observer to another. A description is given of how statistical hypothesis testing can be used to select the quantitative descriptors best capable of distinguishing between normal and abnormal liver texture. Information is also presented on how both parametric and nonparametric discriminant analysis can be applied to determine how well the quantitative analysis compares with the qualitative diagnosis supplied for each case studied.

While cooccurrence matrices have been shown to be helpful in quantitating image texture, the amount of data associated with them can rapidly become unmanageable because a separate cooccurrence matrix can be calculated for each displacement vector chosen. Here, a method for choosing the direction of the displacement vector that is based on the most dominant edge obtained from gradient analysis is discussed. Also, the anatomy of the liver is used to suggest the most important intersample spacing in constructing cooccurrence matrices for the evaluation of diffuse liver disease.

Spectral analysis of Doppler ultrasound has been known to yield valuable information to assess the state of circulation in the peripheral blood vessels. In the past, the raw Doppler data have been directly input into a dedicated spectrum analyzer or, more recently, transformed on a microcomputer with the fast Fourier technique. The fast Hartley technique is used to transform these data. The Hartley transform has the advantages of being a purely real-numbered transform, and therefore for real Doppler data, is not only more conceptually straightforward, but also requires less computer memory, is simpler to calculate, and is better suited to large-scale integration implementation. © 1988 IEEE

Recent developments in image digitization have made possible a more quantitative analysis of ultrasonic imagery of the liver, which could lead to a more sensitive method for changes in liver texture as an aid in the diagnosis of liver disease. The approach described is the statistical analysis of one-dimensional intensity (gray-level) histograms obtained from B-mode ultrasonic images. First-order statistical parameters are used to characterize the location, variability, skewness and kurtosis of the histograms. One typical normal study and one typical abnormal study are presented to shown the type of results that have been obtained.

A new type of RC op oscillator has been designed. For amplitude stabilization, diodes are added in the feedback of the linear circuit. A model has been developed for a nonlinear element, which affects the frequency of oscillation. The model can be used to design the oscillator for different frequencies and to calculate frequency and amplitude sensitivity with respect to the parameter of the system.

A personal computer applications course has been developed. This course is a follow up to an introductory programming course for non-computer science majors. The primary objective of the course is to introduce the major personal computer applications areas: operating system use, word processing, spreadsheet programming, data base management, and communications. For each area, there will be a discussion of its use and related problems. Students will use a representative and a comparison will be made with other systems. The course will be taught using Apple IIe's or Commodore 64 computers. A course outline has been created and approved. The course will be offered for the first time in the Spring of 1984. Budget considerations, the practical difficulties involved with students using copyrighted software, and a desire to have students leave with software they can take with them, make it attractive to use public domain software when possible. Current research is directed towards finding and documenting public domain software for use in this course. Principal sources being investigated are the program libraries of personal computer users groups and educational cooperatives.

Pattern recognition techniques for cloud type and cloud amount classification were applied to digital infrared SMS-1 data. The cloud classification results were used in a numerical radiation model to determine solar radiation during Phase III of the GARP Atlantic Tropical Experiment. In order to assess the effects on radiation computations of cloud information derived from both satellite and ship data, cloud analyses based on both data sources were prepared for input into the numerical radiation model. -from Authors

The backpropagation method is modified by replacing sigmoid function by sinusoidal function. The leaving law is also modified. The modified procedure shows great improvement over the original BP in terms of the number of neurons and the learning time. © 1992 IEEE.

New systolic architectures are proposed for the computation of the Fourier transform based on the generation of the coefficients of the transform during the computation. These architectures require less input/output pins on the chip. The new architectures are also extremely modular and cascadeable, thus, amenable for efficient VLSI implementation. VLSI complexity of the architectures are compared with the existing parallel architectures. © 1992 IEEE.

The increasing prevalence of multiprocessor and distributed systems in modern society is making it imperative to introduce the underlying principles of parallel/distributed computing to students at the undergraduate level. In order to meet the needs of our students for training in this critical area, the Computer Science Department at Southern Connecticut State University (SCSU) is currently in the process of implementing a curricular and laboratory development project that integrates key concepts and practical experiences in parallel computing throughout the undergraduate curriculum. The goal of this project is to build a strong foundation in parallel computing which would optionally culminate in advanced, senior-level specialized courses in parallel computing and/or senior research projects. This paper describes the laboratory facility we developed to support instruction in parallel and distributed computing and the parallel computing modules which were incorporated into three of our core undergraduate courses: data structures, operating systems, and programming languages. The laboratory facility enables us to provide our students with "hands-on" experiences in shared memory, distributed memory, and network parallelism. The modules and laboratory exercises give students the opportunity to experiment with a wide array of software and hardware environments and to gain a systematic exposure to the principles and techniques of parallel programming.

For the TREC 2007 conference, the CRM114 team considered three non-Bayesian methods of spam filtration in the CRM114 framework - an SVM based on the "hyperspace" feature==document paradigm, a bit-entropy matcher, and substring compression based on LZ77. As a calibration yardstick, we used the well-tested and widely used CRM114 OSB markov random field system (basically unchanged since 2003). The results show that the SVM has a spam-filtering accuracy of about a factor of two to three better accuracy than the OSB system, that substring compression is somewhat more accurate than OSB, and that bit entropy is somewhat less accurate for the TREC 2007 test sets.

There have been a large number of projects based on the Distributed Object Oriented (DOO) approach for solving complex problems in various scientific fields. The Mismatch problem is one of the most important problems facing the DOO system, where the initial design of the DOO application does not give the best class distribution. In such a case, the DOO software may need to be restructured. In this paper, we propose a methodology for efficiently restructuring the DOO software classes to be mapped on a distributed system consisting of a set of nodes. The proposed methodology consists of two phases. The first phase introduces a recursive graph clustering technique to partition the OO system into subsystems with low coupling. The second phase is concerned with mapping the generated partitions to the set of available machines in the target distributed architecture. A simulation evaluation was carried out for a set of randomly generated DOO software designs. Then the results were compared with those of the K-Partitioning algorithm in terms of the overall inter-class communication cost. © 2008 IEEE.