Ensuring the safety and efficiency of Autonomous Vehicles (AVs) necessitates highly accurate perception, especially for lane detection and lane-change manoeuvres. Among object detection frameworks, “You Only Look Once” (YOLO) algorithms have emerged as prominent contenders due to their rapid inference and commendable accuracy. However, the broad spectrum of YOLO variants and their applications in complex, real-world environments remain insufficiently mapped, necessitating a more integrative and critical perspective than what is typically offered by surveys. This comprehensive review synthesizes theoretical foundations, architectural innovations, and empirical evaluations of YOLO-based algorithms in AV-related tasks. It not only highlights key findings—such as the notable gains in real-time detection and adaptability to a range of driving conditions—but also explicitly identifies persistent gaps and limitations. These include difficulties in detecting subtle or degraded lane markings, handling unpredictable environmental factors like adverse weather and varied lighting, mitigating adversarial perturbations, and scaling effectively across diverse datasets and geographic regions. By critically examining these vulnerabilities, we illuminate the opportunities for refining YOLO's training paradigms, optimizing model architectures, incorporating sensor fusion, and fostering universally applicable datasets. The implications of addressing these gaps extend beyond mere technical refinements. Proactively tackling YOLO's current challenges can expedite the realization of safer, more robust, and globally adaptable AV navigation systems. In doing so, this review provides clear, actionable insights for researchers, engineers, and policymakers, guiding them toward strategic innovations that will strengthen AV perception and contribute to more reliable, future-ready transportation solutions.

With the rapid development of satellite technology, communication satellites have become an indispensable part of modern infrastructure. They serve as a key pillar for the future integrated communication satellite network (CSN). However, the increasing number of communication satellites presents significant challenges for data transmission between the satellite and ground station. This article focuses on transmitting communication data by scheduling resources for communication tasks. The goal of data transmission scheduling optimization in CSN (DTSOCSN) is to design a scheduling scheme that maximizes task profit across satellite–ground links, considering the constraints of the two working modes of communication satellites. To solve DTSOCSN, a mixed-integer programming model is developed, which incorporates various constraints such as the conditions for feed switching operation and the limitations of task execution windows. Based on the complexity of the problem, we propose an evolutionary algorithm with memory guidance (MGEA). The algorithm takes into account the memory dependence of Caputo fractional-order differential and innovatively designs a crossover operator, called Caputo crossover (CX). This crossover method uses the genetic information stored in memory to guide the crossover operation of the next generation, thereby forming a smooth optimization path and improving the search efficiency of the algorithm. In addition, an elite opposition-based heuristic initialization method and a tracking variation strategy are designed to enhance the algorithm’s ability to find high-quality initial solutions and perform local optimization. Experimental validation proceeds in two stages: first, multiscale simulations demonstrate MGEA’s superior performance over existing mainstream algorithms in task profit, convergence speed, resource utilization, and search efficiency. Second, to verify the contribution of the CX operator, it is integrated into several classical algorithms for comparative testing on benchmark problems. The results consistently show that algorithms using the CX operator achieve significant performance advantages compared with those relying on traditional crossover operators. This study not only provides an effective solution for DTSOCSN but also offers new idea for solving other types of satellite scheduling problems.

Traditional Adaptive Cruise Control (ACC) systems often struggle to dynamically adapt to rapidly changing traffic conditions, resulting in suboptimal performance. Additionally, with fuel consumption emerging as a critical consideration alongside safety, there is a pressing need for more advanced solutions. This paper presents a novel approach to address these challenges by integrating Fuzzy ACC with Model Predictive Control , denoted as FACMPC. This integration aims to enhance both the longitudinal safety of AVs and fuel efficiency by considering real-time traffic conditions. The FACMPC system utilizes fuzzy logic inside the MPC, adaptively generates controller's weighting factors, allowing the system to adapt instantly to varying traffic environments and driving circumstances. The findings show that this adaptation improves the balance between driving safety, efficiency, and comfort. Additionally, three interruption scenarios, Alpha, Beta and Gama, are examined. In Alpha, the study evaluates the sensitivity of the FACMPC to disturbances by applying band-limited white noise to the lead vehicle velocity. In Beta, the AV experiences a loss of the lead vehicle velocity signal for a defined period, prompting safety considerations and assumptions. The Gama scenario includes a sensitivity analysis to account for variations and uncertainties in parameters by considering a range of ±5% around the nominal values for four key parameters: road slope, wind speed , wind direction, and rolling resistance. The findings indicate that the proposed controller's mean fuel consumption is 8.110, only a 3.21% increase over the nominal, compared to a 7.03% increase for the conventional ACC, demonstrating greater robustness against uncertainties.

Cooperative co-evolution (CC) is a practical and efficient evolutionary framework for solving large-scale global optimization problems (LSGOPs). The performance of CC depends on how variables are being grouped and can be improved through guided variable decomposition for various optimization problems. However, achieving a proper variable decomposition is computationally expensive. This article proposes an effective yet efficient differential grouping (EDG) method to reduce the associated computational cost. Our method exploits the historical interrelationship information of previous variable groups to examine interactions between the remnant variable groups. This allows us to spend less computing resources without compromising the accuracy of the final grouping result. Our proposal utilizes the covariance matrix adaptation evolution strategy (CMA-ES) algorithm, in conjunction with EDG, to solve LSGOPs. Further, to reduce time complexity and improve the stability of CMA-ES, we substitute the complex matrix decomposition step with simpler matrix operations to compute the square root of the covariance matrix. Results from our experiments and analysis indicate that EDG is a competitive method to solve LSGOPs and improve the performance of CC. The proposed schemes significantly enhance the searchability of CMA-ES compared to the other large-scale variants of CMA-ES and state-of-the-art large-scale optimizers. Moreover, our EDG could be integrated with evolutionary optimizers of different flavors like differential evolution (DE).

Autonomous vehicles (AVs) have a significant impact on the expansion of greenhouse gas emissions as well as driving safety. Consequently, ensuring safety while improving the energy efficiency of AVs has gained increasing importance. In this study, we offer an optimal intelligent system (OIS) by applying a multi-objective evolutionary optimization algorithm to an integrated control system, including an Adaptive Cruise Control (ACC) and an Intelligent Energy Management System (IEMS) that augments safety and lessens the energy consumption for Conventional AVs. In this - system, a predictive model is developed by defining the desired acceleration of the ego vehicle. The vehicle then follows a longitudinal path to track the lead vehicle on the same highway lane, ensuring a safe following distance while minimizing tracking errors. Subsequently, an Intelligent Energy Management System (IEMS) is introduced to optimize the torque output of the internal combustion engine, aimed at reducing the energy consumption of the ego vehicle. Additionally, a sensitivity analysis of the ego vehicle is conducted to account for disturbances and signal loss scenarios. In this way, a band-limited white noise is considered for road power demand (RPD) and measuring signal of lead vehicle velocity, simultaneously. Moreover, two different scenarios are designed regarding signal-losing circumstances and interruptions in receiving the signal of lead vehicle velocity. The optimal solutions reveal a strong independence between safety and fuel consumption, showing that their performances significantly affect each other. The optimal solutions reveal a strong interdependence between safety and fuel consumption, showing that their performances significantly affect each other. The results demonstrate that the optimal approach can significantly reduce fuel consumption while maintaining safety and effective collision avoidance performances.

The mean shift algorithm is a simple yet very effective clustering method widely used for image and video segmentation as well as other exploratory data analysis applications. Recently, a new algorithm called MeanShift++ (MS++) for low-dimensional clustering was proposed with a speedup of 4000 times over the vanilla mean shift. In this work, starting with a first-of-its-kind theoretical analysis of MS++, we extend its reach to high-dimensional data clustering by integrating the Uniform Manifold Approximation and Projection (UMAP) based dimensionality reduction in the same framework. Analytically, we show that MS++ can indeed converge to a non-critical point. Subsequently, we suggest modifications to MS++ to improve its convergence characteristics. In addition, we propose a way to further speed up MS++ by avoiding the execution of the MS++ iterations for every data point. By incorporating UMAP with modified MS++, we design a faster algorithm, named UMAP embedded quick mean shift (UEQMS), for partitioning data with a relatively large number of recorded features. Through extensive experiments, we showcase the efficacy of UEQMS over other state-of-the-art algorithms in terms of accuracy and runtime.

Gaussian Adaptation (GaA) is a black box op-timization algorithm that shares a similar evolution process with the well-studied Simulated Annealing (SA) and Covariance Matrix Adaptation Evolution Strategy (CMA-ES). To improve the convergence properties of GaA in optimization, this paper presents a variant of GaA that degenerates during its evolution process into algorithms with well-proven convergence properties. Specifically, the proposed GaA variant termed AwGaA employs an adaptive weighting of the covariance matrix update of the standard GaA. Consequently, as the evolution process progresses the algorithm degenerates into a variant of SA or (1+1)-CMA-ES. The performance of the proposed AwGaA is evaluated on 30 functions from the IEEE 2014 benchmark suite and compared favorably with the original GaA as well as 6 other leading algorithms.

Due to the scarcity of labeled data, Contrastive Self-Supervised Learning (SSL) frameworks have lately shown great potential in several medical image analysis tasks. However, the existing contrastive mechanisms are sub-optimal for dense pixel-level segmentation tasks due to their inability to mine local features. To this end, we extend the concept of metric learning to the segmentation task, using a dense (dis)similarity learning for pre-training a deep encoder network, and employing a semi-supervised paradigm to fine-tune for the downstream task. Specifically, we propose a simple convolutional projection head for obtaining dense pixel-level features, and a new contrastive loss to utilize these dense projections thereby improving the local representations. A bidirectional consistency regularization mechanism involving two-stream model training is devised for the downstream task. Upon comparison, our IDEAL method outperforms the SoTA methods by fair margins on cardiac MRI segmentation. Our source codes are publicly accessible at: https://github.com/Rohit-Kundu/IDEAL-ICASSP23.

Socially aware robotic applications such as companion and therapeutic robots usually require human emotions or intent to be conveyed. As the scope of these applications increases, the need for recognizing affective touch gestures which are often used to convey these emotions or intent becomes eminent. However, existing touch gesture recognition modalities either have low recognition accuracy or depend heavily on carefully hand-crafted features, therefore limiting their deployment in real-life applications. Motivated by the need for learning models with superior accuracy which do not rely on manually selected hand-crafted features, this paper proposes an optimized class-weighted CNN-LSTM for social touch gesture recognition evaluated on the CoST and HAART datasets. Specifically, contrary to vanilla training schemes where equal importance is given to each class in the dataset, different class weights are introduced to give priority to classes that are difficult for the network to distinguish during training. Furthermore, the weights associated with each of the classes are obtained through optimization using Genetic Algorithm. The proposed model demonstrates superior performance compared with other existing models in the literature.

In machine learning and computer vision, mean shift (MS) qualifies as one of the most popular mode-seeking algorithms used for clustering and image segmentation. It iteratively moves each data point to the weighted mean of its neighborhood data points. The computational cost required to find the neighbors of each data point is quadratic to the number of data points. Consequently, the vanilla MS appears to be very slow for large-scale datasets. To address this issue, we propose a mode-seeking algorithm called GridShift, with significant speedup and principally based on MS. To accelerate, GridShift employs a grid-based approach for neighbor search, which is linear in the number of data points. In addition, GridShift moves the active grid cells (grid cells associated with at least one data point) in place of data points towards the higher density, a step that provides more speedup. The runtime of Grid Shift is linear in the number of active grid cells and exponential in the number of features. Therefore, it is ideal for large-scale low-dimensional applications such as object tracking and image segmentation. Through extensive experiments, we showcase the superior performance of GridShift compared to other MS-based as well as state-of-the-art algorithms in terms of accuracy and runtime on benchmark datasets for image segmentation. Finally, we provide a new object-tracking al-gorithm based on GridShift and show promising results for object tracking compared to CamShift and meanshift++.

During the last two decades, the notion of multiobjective optimization (MOO) has been successfully adopted to solve the nonconvex constrained optimization problems (COPs) in their most general forms. However, such works mainly utilized the Pareto dominance-based MOO framework while the other successful MOO frameworks, such as the reference vector (RV) and the decomposition-based ones, have not drawn sufficient attention from the COP researchers. In this article, we utilize the concepts of the RV-based MOO to design a ranking strategy for the solutions of a COP. We first transform the COP into a biobjective optimization problem (BOP) and then solve it by using the covariance matrix adaptation evolution strategy (CMA-ES), which is arguably one of the most competitive evolutionary algorithms of current interest. We propose an RV-based ranking strategy to calculate the mean and update the covariance matrix in CMA-ES. Besides, the RV is explicitly tuned during the optimization process based on the characteristics of COPs in a RV-based MOO framework. We also propose a repair mechanism for the infeasible solutions and a restart strategy to facilitate the population to escape from the infeasible region. We test the proposal extensively on two well-known benchmark suites comprised of 36 and 112 test problems (at different scales) from the IEEE CEC (Congress on Evolutionary Computation) 2010 and 2017 competitions along with a real-world problem related to power flow. Our experimental results suggest that the proposed algorithm can meet or beat several other state-of-the-art constrained optimizers in terms of the performance on a wide variety of problems.

In this paper, a novel hybrid discrete differential evolution based approach is proposed to address a single machine scheduling problem where each job has a release date and the tardiness cost of the job increases stepwise with respect to various due dates. In the literature, this problem is termed as the single machine total stepwise tardiness problem with release dates (SMTSTP-R). The objective of the problem is to find a schedule of jobs which minimizes the total tardiness cost. The stepwise increase in tardiness cost is more prevalent in several real life scenario, especially in transportation. We have used two constructive heuristics and concept of opposition based solutions to generate initial population. Our proposed approach uses a series of local searches to further enhance the quality of solutions obtained by the proposed discrete differential evolution approach. In order to justify the superiority of proposed approach, various comparisons are done with the existing approaches available in the literature. The results of these comparisons validate the superiority of our approach in comparison to the existing state-of-the-art approaches.

Classical clustering methods usually face tough challenges when we have a larger set of features compared to the number of items to be partitioned. We propose a Sparse MinMax k-Means Clustering approach by reformulating the objective of the MinMax k-Means algorithm (a variation of classical k-Means that minimizes the maximum intra-cluster variance instead of the sum of intra-cluster variances), into a new weighted between-cluster sum of squares (BCSS) form. We impose sparse regularization on these weights to make it suitable for high-dimensional clustering. We seek to use the advantages of the MinMax k-Means algorithm in the high-dimensional space to generate good quality clusters. The efficacy of the proposal is showcased through comparison against a few representative clustering methods over several real world datasets.

The maximum scatter traveling salesman problem (MSTSP) is a variant of the well-known traveling salesman problem (TSP) where the objective is to find a Hamiltonian cycle on a graph that maximizes the minimum length among its constituent edges. The MSTSP finds important application in manufacturing and medical imaging. In this study, we propose a multi-start iterated local search algorithm for the MSTSP. Two local search algorithms based on insertion and modified 2-opt moves have been developed as part of our approach. To investigate the performance of the proposed approach, benchmark instances from the standard TSPLIB are used. Computational results and their analysis show the effectiveness of the proposed approach.

In this letter, an efficient indicator for multi and many-objective optimization is proposed. The proposed indicator (ISDE+) is a combination of sum of objectives and shift-based density estimation and benefits from their ability to promote convergence and diversity, respectively. An evolutionary multiobjective optimization framework based on the proposed indicator is shown to perform comparably or better than the state-of-the-art on a variety of scalable benchmark problems.

Main objective of this work is to analyze the ability of the Differential Evolution (DE) framework equipped with a multi-donor mutation strategy and annealing-based local search technique to find the global minimum of the potential energy functions, which are used for molecular cluster modeling. Finding such stable molecular clusters is a significant and well-established optimization problem arising from the area of molecular distance geometry and has important implications in artificial drug design as well. Results for moderate (3, 5, 10, 15, 20, 25, and 30 atomic molecules) scale problems are presented here for the Lennard-Jones potential function based atomic clusters. Our experiments reveal that the proposed DE variant is able to yield better results than the competing state-of-art DE based optimizers and the results are with par to the best results listed in the Cambridge energy landscape database (http://doye.chem.ox.ac.uk/jon/structures/LJ.html).

In smart grid, energy resource management is highly complex large-scale optimization problem where the aim is to maximize the incomes while minimizing operational costs. Due to presence of mixed-integer variables and non-linear constraints, recently the use of evolutionary algorithms as a tool to find optimal and near-optimal solutions is becoming popular. The energy resource management problem further gets complicated if the uncertainty associated with the renewable generation, load forecast errors, electric vehicles scheduling and market prices are considered. Therefore, in a real-world scenario, it is essential to address the issues brought by the variability of demand, renewable energy, electric vehicles, and market price variations while maximizing the incomes and minimizing the total operation costs. In this paper, we analyze the performance of Differential Evolution with a stochastic selection on a large-scale energy resource management problem with uncertainty designed for competition at CEC 2018. The system comprises of a 25-bus microgrid representing a residential area with high penetration of Distributed Energy Resources (DER), Electric Vehicles (EVs), Demand Response (DR) programs etc.

In non-intrusive load monitoring, identification of electrical loads based on single point measurement of different energy related parameters plays a significant role. In literature, different conventional features such as true power, reactive power, RMS voltage, RMS current, phase angle and frequency in addition to the non-conventional features were employed. In addition, a variety of classifiers such as k-nearest neighbors (k-NN), support vector machine (SVM), random forest and Gaussian mixture models (GMM) have been employed. In this paper, we demonstrate that the classification performance strongly depends on the classifier and associated features selected. The experiments are performed on ACS-F2 Database of Appliance Consumption Signatures consisting of 225 devices belonging to 15 different categories.

Brain-Computer Interfaces (BCIs) systems convert brain signals into outputs commands those allow to user to communicate even absence of other body nerves and muscles activities. Response to cognitive activity (mental task) grounded BCI system is one of the dominate areas of research interest. Electroencephalography (EEG) signals are utilized to characterize the brain activities in the BCI domain. Efficient feature extraction from EEG signal is the most important aspect of good per-formance of classification model. Two known feature extraction methods for non-linear and non-stationary signals are Wavelet Transform and Empirical Mode Decomposition. By exploiting both techniques, an adaptive-filter based approach was proposed earlier famous as Empirical Wavelet Transform (EWT) to de-compose such dynamic signals. But EWT failed to provide useful features for dynamic signals which has overlapping in frequency domain and time domain. To overcome this problem, we utilized fuzzy c-means algorithm along with EWT in our experiment. A well-known multivariate feature selection technique named Linear Regression is used to avoid the problem of the small ratio of samples to features. Further, the Quadratic discriminant classifier (QDC) has been utilized to develop the classification model. The experiments have been done on a publicly available task-based EEG data for comparing the proposed approach with EWT based cognitive activity (mental task) classification. The experimental results show that the proposed fuzzy-based EWT approach for EEG classification gives superior performance over the original EWT.

Differential Evolution (DE), a population-based stochastic search technique is adept at solving real-world optimization problems. Unlike most population based algorithms, the use of DE is usually inexpedient in solving expensive optimization problems as the computational costs of these simulations are excessively high. This problem can be resolved by commingling surrogate model in DE that approximates the output behavior of complex systems based on a limited set of expensive simulations. Surrogate models are compact and cheap to evaluate and have proven very useful for solving expensive optimization tasks. Though, the use of a surrogate model can address the expensive problems, the optimization based on a single surrogate can lead to premature convergence. DE fused with an ensemble of surrogates, each having different roles and features reports more precise results. In this paper, we present a novel method in which DE is integrated with an ensemble of low-quality surrogate models. The proposed algorithm is referred to as DE-ELS (Differential evolution with an ensemble of low-quality surrogate models) and employs polynomial regression, Kriging, and Nearest Neighbors technique for constructing the surrogates. The performance of DE-ELS is evaluated on a set of 8 bound-constrained problems and is compared with state-of-the-art algorithms belonging to IEEE-CEC 2014 competition test suite.

In this paper, we propose a framework that can prevent accidents due to careless or inattentive driving by providing the necessary traffic information to the driver. The proposed system complements the driver by providing the missed cognitive information regarding the traffic. The proposed system is divided into three parts. First, the system checks the condition of the driver in real time, and detects the status of the driver in terms of driving ability. Second, we propose bottom-up and top-down processes based on Traffic Information Saliency Map (TISM) which contains the distribution corresponding to the external road information using bottom-up traffic information saliency map and top-down importance information such as pedestrian and traffic light detection results. Computer experimental results show that the proposed method works well for monitoring of internal situation for driver's attention as well as external environment.

Palmprint recognition is a challenging problem, mainly due to low quality of the patterns, variation in focal lens distance, large nonlinear deformations caused by contactless image acquisition system, and computational complexity for the large image size of typical palmprints. This paper proposes a new contactless biometric system using features of palm texture extracted from the single hand image acquired from a digital camera. In this work, we propose to apply convolutional neural network (CNN) for palmprint recognition. The results demonstrate that the extracted local and general features using CNN are invariant to image rotation, translation, and scale variations.

We propose a smart cane with a face recognition system to help the blind in recognizing human faces. This system detects and recognizes faces around them. The result of the detection is informed to the blind person through a vibration pattern. The proposed system was designed to be used in real-time and is equipped with a camera mounted on the glasses, a vibration motor attached to the cane and a mobile computer. The camera attached to the glasses sends image to mobile computer. The mobile computer extracts features from the image and then detects the face using Adaboost. We use the modified census transform (MCT) descriptor for feature extraction. After face detection, the information regarding the detected face image is gathered. We used compressed sensing with L2-norm as a classifier. Cane is equipped with a Bluetooth module and receives a person's information from the mobile computer. The cane generates vibration patterns unique to each person as to inform a blind person about the identity of the detected person using the camera. Hence, the blind people can know the person standing in front of them.

This paper proposes an agent to assist human cognition in memorizing multiple human faces by analyzing user's eye gaze points. The gaze point which is the direction of sight is obtained by the infrared camera on a glass-type agent with the help of an embedded module. The gaze information is then combined with the image captured by the frontal camera to identify the location of the face that the user is looking at among several faces. The gaze detection and face selection with tracking are performed in embedded modules attached to the glass-type agent, and the recognition of the selected facial images is performed and shown on a mobile computer connected via wireless network. The major contribution of the proposed work is the use of eye gaze direction to select faces of interest, and provide information regarding the faces to improve human memory capability in recalling the faces.

In Advanced Driving Assistance Systems (ADASs), monitoring the driver's cognitive status during driving is considered as an important issue. Because, most of the accidents in the automotive sector occur due to the driver's misinterpretation or lack of sufficient information regarding the situation. In order to prevent these accidents, current ADASs include lane departure warning systems, vehicle detection systems, advanced cruise control systems, etc. In a particular driving scenario, the amount of information available to the driver regarding a situation can be judged by monitoring the driver's gaze (internal information) and distributions corresponding to the forward traffic (external information). Therefore, to provide sufficient information to the driver regarding a driving scenario it is essential to integrate the internal and external information which is lacking in the current ADASs. In this paper, we use 3D pose estimate algorithm (POSIT) to estimate driver's attention area. In order to estimate the distributions corresponding to the forward traffic we employ Bottom-up Saliency map. To integrate the internal and external information we use conditional mutual information.

This paper presents a real-time hand gesture detection and recognition method. Proposed method consists of three steps - detection, validation and recognition. In the detection stage, several areas, estimated to contain hand shapes are detected by random forest hand detector over the whole image. The next steps are validation and recognition stages. In order to check whether each area contains hand or not, we used Linear Discriminant Analysis. The proposed work is based on the assumption that samples with similar posture are distributed near each other in high dimensional space. So, training data used for random forest are also analyzed in three dimensional space. In the reduced dimensional space, we can determine decision conditions for validation and classification. After detecting exact area of hand, we need to search for hand just in the nearby area. It reduces processing time for hand detection process.

Images can convey emotion just like music. If that's so, then it might be possible that, given an image, one can obtain a music that can produce a similar reaction from the listener/viewer. The challenge lies in how to do that. In this paper, we analyze the image using the HSV color space model and assume that each one of the three components have a relation with basic music elements, like tone, pitch, rhythm and loudness. The image is then scanned from left to right and top to bottom in order to generate a sequence of notes. In the end, the emotional Mean Opinion Score (MOS) is used to evaluate the performance of the proposed method. This work could prove to be a very important contribution to the field of HCI because it can improve the interaction between computers and humans who are visually and/or hearing impaired. In the current work, we only consider two emotions; positive and negative.

Motion understanding and regeneration are two basic aspects of human-agent interaction. One important function of agents is to represent human's activities. For better interaction with human, robot agents should not only do something following human's order, but also be able to understand or even play some actions. Multiple Timescale Recurrent Neural Networks (MTRNN) is believed to be an efficient tool for robots action generation. In our previous work, we extended the concept of MTRNN and developed Supervised MTRNN for motion recognition. In this paper, we use Conditional Restricted Boltzmann Machine (CRBM) to initialize Supervised MTRNN and accelerate the training speed of Supervised MTRNN. Experiment results show that our method can greatly increase the training speed without losing much performance.

Intention understanding is a basic requirement for human-machine interaction. Action classification and object affordance recognition are two possible ways to understand human intention. In this study, Multiple Timescale Recurrent Neural Network (MTRNN) is adapted to analyze human action. Supervised MTRNN, which is an extension of Continuous Timescale Recurrent Neural Network (CTRNN), is used for action and intention classification. On the other hand, deep learning algorithms proved to be efficient in understanding complex concepts in complex real world environment. Stacked denoising auto-encoder (SDA) is used to extract human implicit intention related information from the observed objects. A feature based object detection method namely Speeded Up Robust Features (SURF) is also used to find the object information. Object affordance describes the interactions between agent and the environment. In this paper, we propose an intention recognition system using `action classification' and `object affordance information'. Experimental result shows that supervised MTRNN is able to use different information in different time period and improve the intention recognition rate by cooperating with the SDA.

Recent developments in vision systems such as distributed smart cameras have encouraged researchers to develop advanced computer vision applications suitable to embedded platforms. In the embedded surveillance system, where memory and computing resources are limited, simple and efficient computer vision algorithms are required. In this letter, we present a moving object detection method for real-time traffic surveillance applications. The proposed method is a combination of a genetic dynamic saliency map (GDSM), which is an improved version of dynamic saliency map (DSM) and background subtraction. The experimental results show the effectiveness of the proposed method in detecting moving objects.

Differential Evolution (DE), a global optimization algorithm based on the concepts of Darwinian evolution, is popular for its simplicity and effectiveness in solving numerous real-world optimization problems in real-valued spaces. The effectiveness of DE is due to the differential mutation operator that allows DE to automatically adjust between the exploration/exploitation in its search moves. However, the performance of DE is dependent on the setting of control parameters such as the mutation factor and the crossover probability. Therefore, to obtain optimal performance preliminary tuning of the numerical parameters, which is quite timing consuming, is needed. Recently, different parameter adaptation techniques, which can automatically update the control parameters to appropriate values to suit the characteristics of optimization problems, have been proposed. However, most of the adaptation techniques try to adapt each of the parameter individually but do not take into account interaction between the parameters that are being adapted. In this paper, we introduce a DE self-adaptive scheme that takes into account the parameters dependencies by means of a multivariate probabilistic technique based on Gaussian Adaptation working on the parameter space. The performance of the DE algorithm with the proposed parameter adaptation scheme is evaluated on the benchmark problems designed for CEC 2014.

Most of the machine learning algorithms particularly suffer from the plasticity-stability dilemma. In this paper, we propose a model that adopts two types of memories i.e. short-term memory (STM) and long-term memory (LTM), which share their information through control processes called rehearsal and recall to alleviate the dilemma. In addition, the proposed model tries to integrate the advantages of generative and discriminative classifiers by employing them in STM and LTM respectively. Experimental results show the importance of rehearsal and recall process in improving the performance of the algorithm.

In this paper, we present a method to track moving vehicles in low frame rate videos which are common in embedded traffic surveillance systems. In general, an embedded surveillance system has limited memory and computing resources, and thus the frame rate of video dramatically decreases. Hence, the features of moving vehicles such as shapes and sizes vary dramatically which is difficult to be handled using appearance and/or feature based conventional methods. In the proposed model, the probability distribution of a tracking vehicle in the next frame is predicted based on a hypothesis which is constructed by trajectory identification model using manifold learning. By the projecting on the low dimensional manifold, the probabilistic similarity between the observed and the predicted probability distributions of the tracking vehicles is measured. The probabilistic distribution with maximum similarity among several candidate hypotheses in the trajectory identification models is considered to include spatial information to track a moving vehicle. Experimental results show the effectiveness of the proposed method in tracking moving vehicles, even when the shapes, positions and sizes change rapidly.

Differential Evolution (DE) is a simple and effective approach for solving numerical optimization problems. However, the performance of DE is sensitive to the choice of the mutation and crossover strategies and their associated control parameters. Therefore, to obtain optimal performance, time consuming parameter tuning is necessary. In DE, different mutation and crossover strategies with different parameter settings can be appropriate during different stages of the evolution. Therefore, to obtain optimal performance using DE, various adaptation and self-adaptation techniques have been proposed. Recently, a DE algorithm with an ensemble of parameters and strategies (EPSDE) was proposed. In EPSDE, a pool of distinct mutation and crossover strategies along with a pool of values for each control parameter coexists throughout the evolution process and competes to produce offspring. The performance of EPSDE degrades if the population members get struck with a combination of strategies and parameters values that produce successful offspring but lead to premature convergence in the due course of the evolution. In this paper, we try to improve the performance of the EPSDE algorithm with the help of a surrogate model that assists in generating competitive trial vectors corresponding to each parent in every generation of the evolution. The proposed algorithm is referred to as surrogate model assisted EPSDE (SMA-EPSDE) and employs a simple Kriging model to construct the surrogate. The performance of EPSDE is evaluated on a set of 17 bound-constrained problems and is compared with state-of-the-art algorithms.

Principal Component Analysis (PCA) is one of the most widely used subspace projection technique for face recognition. In subspace methods like PCA, feature selection is fundamental to obtain better face recognition. However, the problem of finding a subset of features from a high dimensional feature set is NP-hard. Therefore, to solve the feature selection problem, heuristic methods such as evolutionary algorithms are gaining importance. In many face recognition applications, due to the small sample size (SSS) problem, it is difficult to construct a single strong classifier. Recently, ensemble learning in face recognition is gaining significance due to its ability to overcome the SSS problem. In this paper, the NP-hard problem of finding the best subset of the extracted PCA features for face recognition is solved by using the differential evolution (DE) algorithm and is referred to as FS-DE. The feature subset is obtained by maximizing the class separation in the training data. We also present an ensemble based approach for face recognition (En-FR), where different subsets of PCA features are obtained by maximizing the distance between a subset of classes of the training data instead of whole classes. The subsets of the classes are obtained by bagging and overlap each other. Each subset of the PCA features selected is used for face recognition and all the outputs are combined by a simple majority voting. The proposed algorithms, FS-DE and En-FR, are evaluated on four wellknown face databases and the performance is compared with the PCA and Fisher's LDA algorithms.

Interpretation of human implicit intention is crucial in the development of an efficient nonverbal human computer interaction system. According to cognitive visuo-motor theory, the human eye movements and pupillary responses are rich source of information about the human intention and behavior. It has been observed that under conditions of constant illumination and accommodation, pupil size varies systematically in relation to a variety of physiological and psychological factors, such as level of mental effort. It is well known that pupillary responses could be used to measure the differences in cognitive load under various tasks. In this paper, we try to detect the transition between the different human implicit intents based on the pupil state analysis. In real-world environment, the pupillary response can be influenced by various external factors like intensity and size of the image. To overcome the influence of the external factors, we develop a robust baseline model. The proposed approach detects the transition of the human's implicit intent from navigational intent to informational intent and vice versa during a visual stimulus. The approach also detects the transition among the different states of the informational intent such as informational intent generation, informational intent maintenance and informational intent disappear.

The aim of cognitive augmentation is to expand the intrinsically limited human's cognitive abilities caused by cognitive impairment or disability. In order to assist the human's limited cognitive ability, we are trying to develop a human augmented cognition system that aims to provide the appropriate information actively corresponding to what user intents to do. In this paper, we mainly address the probabilistic human intention modeling for cognitive augmentation, and its overall process. The types of implicit intention such as navigational and informational intention can be predicted by using fixation count and length induced by eyeball movement. Also, the gradient of pupil size variation is used to detect the transition point between navigational intent and the informational intent. A Naïve Bayes classifier is used as a tool for the extraction of query keywords to search and retrieve specific information from personalized knowledge database according to the successive series of attended objects according to a specific informational intent in a situation. The experimental results show that the probabilistic human intention model is suitable for achieving the ultimate purpose of the cognitive augmentation.

Differential Evolution is a population based stochastic algorithm with less number of parameters to tune. However, the performance of DE is sensitive to the mutation and crossover strategies and their associated parameters. To obtain optimal performance, DE requires time consuming trial and error parameter tuning. To overcome the computationally expensive parameter tuning different adaptive/self-adaptive techniques have been proposed. Recently the idea of ensemble strategies in DE has been proposed and favorably compared with some of the state-of-the-art self-adaptive techniques. Compact Differential Evolution (cDE) is modified version of DE algorithm which can be effectively used to solve real world problems where sufficient computational resources are not available. cDE can be implemented on devices such as micro controllers or Graphics Processing Units (GPUs) which have limited memory. In this paper we introduced the idea of ensemble into cDE to improve its performance. The proposed algorithm is tested on the 30D version of 14 benchmark problems of Conference on Evolutionary Computation (CEC) 2005. The employment of ensemble strategies for the cDE algorithms appears to be beneficial and leads, for some problems, to competitive results with respect to the-state-of the-art DE based algorithms.

Differential Evolution (DE) is a simple yet efficient stochastic algorithm for solving real world problems. To achieve optimal performance with DE, time consuming parameter tuning is essential as its performance is sensitive to the choice of the mutation and crossover strategies and their associated control parameters. During different stages of DE's evolution, different combinations of mutation and crossover strategies with different parameter settings can be appropriate. Based on this observation different adaptive and self-adaptive techniques have been proposed. In this paper, we employ a DE with an ensemble of mutation and crossover strategies and their associated control parameters known as EPSDE. In EPSDE, a pool of distinct mutation and crossover strategies along with a pool of values for each control parameter coexists throughout the evolution process and competes to produce offspring. The performance of EPSDE is evaluated on a set of real world problems taken from different fields of engineering and presented in the technical report of Conference on Evolutionary Computation (CEC) 2011.

Several constraint handling techniques have been proposed to be used with the evolutionary algorithms (EAs). According to the no free lunch theorem, it is impossible for a single constraint handling technique to outperform all other techniques on every problem. In other words, depending on several factors such as the ratio between feasible search space and the whole search space, multi-modality of the problem, the chosen EA and global exploration/local exploitation stages of the search process, different constraint handling techniques can be effective on different problems and during different stages of the search process. Motivated by these observations, we proposed an ensemble of constraint handling techniques (ECHT) to solve constrained real-parameter optimization problems. In ECHT, each constraint handling method has its own population and every function call is used effectively. Being a general concept, the ECHT can be realized with any existing EA. In this paper, we present ECHT with Differential Evolution (DE) as the basic search algorithm (ECHT-DE). The ECHT is formed using four different constraint handling techniques present in the literature. ECHT-DE is evaluated on the functions from CEC 2010 problem set.

This paper presents an ensemble of differential evolution algorithms employing the variable parameter search and two distinct mutation strategies in the ensemble to solve real-parameter constrained optimization problems. It is well known that the performance of DE is sensitive to the choice of mutation strategies and associated control parameters. For these reasons, the ensemble is achieved in such a way that each individual is assigned to one of the two distinct mutation strategies or a variable parameter search (VPS). The algorithm was tested using benchmark instances in Congress on Evolutionary Computation 2010. For these benchmark problems, the problem definition file, codes and evaluation criteria are available in http://www.ntu.edu.sg/home/EPNSugan. Since the optimal or best known solutions are not available in the literature, the detailed computational results required in line with the special session format are provided for the competition.

During the last three decades, several constraint handling techniques have been developed to be used with evolutionary algorithms (EAs). According to the no free lunch theorem, it is impossible for a single constraint handling technique to outperform all other techniques on every problem. In other words, depending on several factors such as the ratio between feasible search space and the whole search space, multimodality of the problem, the chosen EA, and global exploration/local exploitation stages of the search process, different constraint handling methods can be effective during different stages of the search process. Motivated by these observations, we propose an ensemble of constraint handling techniques (ECHT) to solve constrained real-parameter optimization problems, where each constraint handling method has its own population. A distinguishing feature of the ECHT is the usage of every function call by each population associated with each constraint handling technique. Being a general concept, the ECHT can be realized with any existing EA. In this paper, we present two instantiations of the ECHT using four constraint handling methods with the evolutionary programming and differential evolution as the EAs. Experimental results show that the performance of ECHT is better than each single constraint handling method used to form the ensemble with the respective EA, and competitive to the state-of-the-art algorithms.

In this paper, we propose a multiobjective self-adaptive differential evolution algorithm with objective-wise learning strategies (OW-MOSaDE) to solve numerical optimization problems with multiple conflicting objectives. The proposed approach learns suitable crossover parameter values and mutation strategies for each objective separately in a multi-objective optimization problem. The performance of the proposed OW-MOSaDE algorithm is evaluated on a suit of 13 benchmark problems provided for the CEC2009 MOEA Special Session and Competition (http://www3.ntu.edu.sg/home/epnsugan/) on Performance Assessment of Constrained/Bound Constrained Multi-Objective Optimization Algorithms.

In Evolutionary Algorithms, the occurrence of premature convergence is due to lack of diversity in the population during the search process. The effect may be more predominant if the optimization problem includes constraints. In this paper we propose an explicit memory based diversity enhancement Adaptive Evolutionary Programming (DivEnh-AEP) method to solve constraint optimization problems of CEC 2006.

In this paper, we investigate the effect of population size on the quality of solutions and the computational effort required by the Differential evolution (DE) Algorithm. A set of 5 problems chosen from the problem set of CEC 2005 Special Session on Real-Parameter Optimization are used to study the effect of population sizes on the performance of the DE. Results include the effects of various population sizes on the 10 and 30-dimensional versions of each problem for two different mutation strategies. Our study shows a significant influence of the population size on the performance of DE as well as interactions between mutation strategies, population size and dimensionality of the problems.

This paper presents empirical studies carried out to evaluate the performance of different constraint handling methods on constrained real-parameter optimization using a novel adaptive evolutionary programming (EP). 25 runs have been conducted for each of the 13 test problems considered. Our experimental results show that no single constraint handling method can be the best for all problems i.e, each constraint handling method is suitable only for a subset of problems. We also show that the novel adaptive EP proposed in this paper has improved performance over the classical EP (CEP).