Over the past ten years, a lot of research has been done on automatic vehicle recognition utilizing machine learning approaches. The majority of earlier research on vehicle detection was done on datasets like as GTI, which mostly comprise well-organized road scenarios. These datasets do not accurately depict road scenes in areas with a lesser transportation infrastructure. As a result, the IDD dataset—which represents unstructured traveling situations—includes a large variety of vehicle classes, and shows adequate intra-class variability for vehicles—has been used to study vehicle recognition in this work. The suggested approach uses three neural networks—DenseNet21, SqueezeNet, and EfficientNet-B0—to extract features, which are then concatenated. An SVM classifier that uses a linear kernel has been trained using this fused collection of features. On a portion of the IDD dataset, the proposed methodology yields 89.73

This study proposes an intelligent educational decision support system that empowers instructional designers to evaluate online educational contents in order to improve their design and effectiveness. The key challenge in developing it lies in automating and objectifying the evaluation process. To address this, the study pursues two main objectives. The first one is to propose a Multicriteria Approach for Learning Experience Analysis (MALEA) on which we have based the evaluation through the learners' traces. The second objective consists of proposing the Approach for Content Success Prediction (ACSP), which can be used to evaluate educational content before its deployment. ACSP combines logistic regression and MALEA. This combination helps to guard against the possible imprecision of human judgment affecting the decision-making process. A case study is conducted and proves that the system meets the objective sought and thus is retained for online educational content evaluation. Results are promising with high values of precision, accuracy, specificity, and sensitivity. Different perspectives are finally proposed.

Today the number of vehicles around is growing exponentially, which has been a cause for concern amongst the population living in major cities, metropolitan areas, and urban areas. As a result of the high traffic volume and limited space in dense urban areas, monitoring vehicles is particularly important [Batavia et al. 1997]. From real-time traffic management to supporting traffic planners, vehicle detection has many valuable applications. It is therefore difficult for law enforcement agencies to monitor every single vehicle. In addition to the rapid growth in the world's population, the number of vehicles on the road is also rising every day. People, their families, and nations are adversely affected by road traffic accidents and injuries. In most countries, road traffic accidents result in a loss of 3% of the Gross Domestic Product (commonly known as GDP) caused by the death of approximately 1.3 million people each year [Sonka et al. 1993]. Despite the fact that there are several accident-avoidance methods available, deep learning-based accident prevention is gaining a lot of attention currently [Maity et al. 2022]. However, deep learningbased methods require more training images and also require more computational resources which may not be available in real-time. So, it is better to apply machine learning-based collision avoidance methods. The collision avoidance algorithm generally involves several steps, including detecting the vehicle and locating it using semantic segmentation, followed by recognizing the segmented objects [Nidhyananthan and Selva 2022]. Data from active sensors has been widely studied in the past few years for object detection. A more important consideration is the cost of these kinds of sensors. Our research focuses on passive sensors such as cameras to detect objects using vision-based methods. Images provide a more detailed picture of the environment than passive sensors. Object detection systems can be designed using the information conveyed by live images. Also, it is advantageous to have a higher resolution. Obtaining on-road information has never been easier, more affordable, and more accessible than with a camera. In addition to being able to use the data from these cameras to enhance intelligent security systems, these images can also be used to minimize traffic congestion through traffic management strategies [Bhattacharya et al. 2022]. Vehicle recognition (or classification) is very crucial for implementing intelligent transportation systems. The purpose of this technique is to identify moving vehicles and classify them accurately based on the flow rate [Arora and Kumar 2022].

Research on plant leaf classification is still ongoing which holds high value in different sectors. Applications of plant leaf classification range from finding new medicines for diseases and tracking the impact of climate change and global warming, and for that we need to have advances on the accuracy of existing algorithms. Therefore, we develop a hybrid feature selection algorithm approach that uses the concept of deep feature optimization which accomplishes well both in terms of computational complexity and classification accuracy. Our model pipeline produces self-learned deep features using pre-trained transfer learning models such as MobileNetV3-Large and EfficientNet from the images of plant leaves. The features sets are merged and the feature dimensionality is reduced using a hybridization of ReliefF and Genetic algorithm. Lastly, a support vector machine (SVM) classifier has been applied to identify the selected feature subset into its corresponding accent classes. The proposed framework has been evaluated on two different widely available plant leaf datasets namely, PlantVillage and Flavia. The proposed pipeline achieves 97.94

Speech serves as the most important means of communication between humans. Every phrase a person speaks has certain emotions intertwined with it. Therefore, a natural desire would be to build a system that understands the mood and feelings of the speaker. Speech emotion detection may have a lot of real-life applications ranging from bettering recommendation systems (which adapt to the emotion user is experiencing) to monitoring people with chronic depression and suicidal tendencies. In this chapter, we propose a model for the recognition of emotions from speech data using log-frequency spectrograms and a deep convolutional neural network (CNN). We supplement our data with the noise of varied loudness obtained from various contexts with the aim of making our model resilient to noise. The augmented data is used for the extraction of spectrograms. These spectrogram images are used to train the deep CNNs, proposed in this paper. The model is independent of linguistic features, speaker-dependent features, the gender of speakers, and the intensity of the expressed emotion. This has been guaranteed by using the RAVDESS dataset, where the same sentences were spoken by 24 speakers (12 male and 12 female) with different expressions (in two levels of intensity). The model obtained an accuracy of 98.13% on this dataset. The experimental results show that our proposed model is quite capable of classifying emotions from human speech. The source code of the proposed model can be accessed using the following link: https://github.com/mainak-biswas1999/Spoken_Emotion_classification.git .

Recommendation systems for suggesting products are crucial, particularly in streaming services. Recommendation algorithms are crucial for helping viewers find new movies they like on streaming movie platforms like Netflix. In this chapter, we create a smart algorithm that makes an optimistic choice to design a collaborative filtering system that forecasts movie ratings for a user based on a significant database of user ratings. According to the genres that users like to watch, it suggests movies that are the greatest fit for them. The cumulative influence of user ratings and reviews produces the list of suggested films. A statistical analysis is performed to develop a pilot survey model to analyze the real-time dataset. Ant Colony Optimization (ACO) is deployed to determine the rating of the group members' for future recommendation. In this way, sparsity problems will be optimized in a recommender system. A real-time dataset named as Movielens is used to validate the proposed model. Finally, deploy k-fold cross validation to evaluate the performance metric.

The stock market is a tough forum for investment and requires ample deliberation before investing hard-earned money into buying stocks. The stock market is one of a number of sectors that buyers are committed to. For this reason, the inventory forecast is a hotly debated topic for researchers from each economic and technical domain. In this chapter, the primary goal is to construct a country-of-art-work prediction for pricing that focuses on quick changes in price predictions. The cryptocurrency market is nowhere near as stable as traditional commodity markets. The stock market can be plagued by numerous technical, emotional, and challenging factors, though, making it extremely volatile, risky, uncertain, and unpredictable. This chapter analyses the shortcomings of the current market tendencies and constructs a time-series version for mitigating most of them by using greater-efficient algorithms. An expert machine is proposed to predict the uncertainty of market risk and to predict the guaranteed amount of return. Fuzzy inference is deployed to predict uncertainty. A real-time data set, the Nifty 50 stock list records (2000–2021), from Kaggle, is used as a test bed to validate the proposed version. Finally, fourfold cross validation is carried out to assess the overall outcome or performance of the proposed model.

Big Data is changing how organizations conduct operations. Data are assembled from multiple points of view through online quests, investigation of purchaser purchasing conduct, and then some, and industries utilize it to improve their net revenue and give an overall better experience to clients. Each of these organizations must figure out how to improve the general client experience and meet every client’s novel necessities, and big data helps with this cycle. Through the utilization and reviews of Big Data, travel industry organizations can study the inclinations of more modest portions of their intended interest group or even about people in some cases. In this paper, a Crow Search Optimization-based Hybrid Recommendation Model is proposed to get accurate suggestions based on clients’ preferences. The hybrid recommendation is performed by combining collaborative filtering and content-based filtering. As a result, the advantages of collaborative filtering and content-based filtering are utilized. Moreover, the intelligent behavior of Crows’ assists the proper selection of neighbors, rating prediction, and in-depth analysis of the contents. Accordingly, an optimized recommendation is always provided to the target users. Finally, performance of the proposed model is tested using the TripAdvisor dataset. The experimental results reveal that the model provides 58%, 58.5%, 27%, 24.5%, and 25.5% better Mean Absolute Error, Root Mean Square Error, Precision, Recall, and F-Measure, respectively, compared to similar algorithms.

E-learning has gained tremendous popularity. In recent decades, major universities all over the world offer online courses aiming to support student learning performance, yet often exhibit low completion rates. Faced with the challenge of decreasing learners’ dropout rates, e-learning communities are increasingly in need to improve trainings. Machine learning and data analysis have emerged as powerful methods to analyze educational data. They can therefore empower the Technology Enhanced Learning Environments (TELEs). Many research projects have interest in understanding dropout factors related to learners, but few works are committed to refine pedagogical content quality. To address this problem, this paper proposes descriptive statistics analysis to evaluate e-course factors contributing to its success. We take up, at first, the task of analyzing a sample of successful online courses. Then, we manage to identify features that are able to attract a large number of learners, meet their needs and improve their satisfaction. We report findings of an exploratory study that investigates the relationship between course success and the strategy of pedagogical content creation.

The proliferation of the Technology Enhanced Learning Environments (TELE) and the growth of educative data are increasingly motivating researchers to study the potential of new approaches in Artificial Intelligence (AI) applied to the e-learning area. In this paper, we propose a software architecture for educational decision support system. We have experimented it with the free Students' Academic Performance Dataset in the goal of analyzing learning experiences. In our system we have implemented the k-means clustering algorithm to group students based on nine behavioral features. The system was able to identify two clusters of learners according to their learning experience (positive of negative). The main objective of this paper is to show how we can build this kind of systems allowing educative organizations to use their own data extracted from TELE to enable tutors and e-Iearning managers to make informed decisions.

The location selection of distribution center covers one of the important strategic decision issues for the logistics system managers. In view of the inherent uncertainty and inaccuracy of human decision-making, the future behavior of the market and companies, this paper adopts the improved multi-attribute and multi-Actor decision-making (MAADM) method as a fuzzy multi-attribute and multi-actor decision-making (FMAADM) method for solving the selection problem under an uncertain environment. The great strengths of our proposed method are: first, the integration of the decision-makers group preferences into the decision-making process, second, the consideration of the informations related to the alternatives and the criteria weights which are inaccurate, uncertain or incomplete, third, the verification of the obtained solution by both tests of concordance and non-discordance. To validate the FMAADM method, a decision support system was developed. Different experiments were provided based on comparative analysis of results and the sensitivity analysis. These experiments demonstrate the efficiency of our proposed method and its superiority over another existing methods.

E-learning has been receiving increasing attention in recent years. Many educational organizations have implemented Technology Enhanced Learning Environments (TELE) to improve student learning performance. This paper presents an overview of e-learning area, with a goal of providing references to fundamental concepts and identifying challenges for the broad community of e-learning practitioners. Until now, pedagogical content has been considered as a critical issue. Thus, we discuss recent content personalization's studies and the most important approaches. Keywords-E-learning; Technology Enhanced Learning Environments (TELE); Massive Open Online Courses (MOOC); Dropout Problem; E-learning Content Evaluation.

Nowadays, distance learning becomes more diverse and popular. Increasingly universities are currently working to offer their online courses (MOOC, SPOC, SMOC, SSOC, etc.) in the form of courses providing learners with a wide variety of choices. However, this multi-criteria choice is complex. In this paper, we propose a personalized recommendation system based on Deep Reinforcement Learning that suggests for learners a most appropriate course according to specificities of each one such as their profile, needs and competences. To validate our system, the later has been tested over a set of real students. The obtained results of our study are in favor of the robustness of our system.

Javad Basseri/Mehdi Forouzanfar/Rouhollah Feghhi/Mojtaba Joodaki.

The location selection of distribution centers is one of the important strategies to optimize the logistics system. To solve this problem, under certain environment, this paper presents a new multicriteria decision-making method based on ELECTRE I. The proposed method helps decision-makers to select the best location from a given set of locations for implementing. After having identified decision-makers, the criteria, and the set of locations, the factors influencing the selection are analyzed in order to identify the best location. A sensitivity analysis is then performed to determine the influence of criteria weights on the selection decision. The strength of the proposed method is to incorporate decision-makers’ preferences into the decision-making process. In addition, the proposed method considers both quantitative and qualitative criteria. Finally, the selected solution is validated by both tests of concordance and discordance simultaneously. A case study is provided to illustrate the proposed method.

The location selection of distribution centers is one of important strategies to optimize the logistics system. To solve this problem, this paper presents a new multi-actor multi-attribute decision-making method based on ELECTRE I. The proposed method helps decision-makers to select a preferred location from a given set of locations for implementing. The strength of the proposed method is to incorporate the preferences of a set of decision-makers into account, notably the role of their experience into the decision-making process, consider both quantitative and qualitative criteria, take into account both desirable directions (Min and Max) and validate the selected location by both tests of concordance and discordance simultaneously. A case study is provided to illustrate the proposed method.

This paper provides a review on recent efforts and development in urban distribution centers' location selection's problem in two categories including uncertain environment and certain environment problems and their solution methods. Also, it provides an overview on various objectives and criteria used. While there are a few papers related to this topic, we have not seen any comprehensive review papers that can cover it. We believe this paper can be used as a complementary and updated version.