Search

This paper presents a digital image dataset of historical handwritten birth records stored in the archives of several parishes across Sweden, together with the corresponding metadata that supports the evaluation of document analysis algorithms’ performance. The dataset is called SHIBR (the Swedish Historical Birth Records). The contribution of this paper is twofold. First, we believe it is the first and the largest Swedish dataset of its kind provided as open access (15,000 high-resolution colour images of the era between 1800 and 1840). We also perform some data mining of the dataset to uncover some statistics and facts that might be of interest and use to genealogists. Second, we provide a comprehensive survey of contemporary datasets in the field that are open to the public along with a compact review of word spotting techniques. The word transcription file contains 17 columns of information pertaining to each image (e.g., child’s first name, birth date, date of baptism, father's first/last name, mother’s first/last name, death records, town, job title of the father/mother, etc.). Moreover, we evaluate some deep learning models, pre-trained on two other renowned datasets, for word spotting in SHIBR. However, our dataset proved challenging due to the unique handwriting style. Therefore, the dataset could also be used for competitions dedicated to a large set of document analysis problems, including word spotting.

This paper investigates the art design of user interaction experience in mobile systems through the methods of contextual perception and machine learning. The theoretical foundations for the design of intangible cultural heritage interactive display resources include digital display theory, intangible cultural heritage education theory, embodied cognition theory, and gamification design theory. Based on the modelling and analysis of the theoretical foundations, the design principles are derived, including the heritage education principle, the somatic interaction design principle, and the content design principle. In this paper, we use ontologies to construct user knowledge models, fuse multi-situational similarity metrics, screen out candidate neighbour sets through preliminary screening, then combine the user's activity to construct time-based weight tensor scores, use tensor decomposition to obtain recommendation evaluation values, and finally use the recommendation evaluation values to make artistic recommendations. The experimental results show that the algorithm can still obtain a good recommendation implementation in the case of extremely sparse data. The analysis of the fit between augmented reality and folk art appreciation class, as well as the reference to relevant application cases, make design and practice of augmented reality application in folk art appreciation class, try to solve the common problems in folk art appreciation class, analyse the feedback effect and make a summary and outlook.

The application of deep learning techniques in hyperspectral satellite images (HSI) classification has led to a significant increase in accuracy compared to machine learning techniques. The research objective is now shifted toward gaining classification accuracy with less number of spectral bands and training samples. With this research objective, the recent development of the hybrid convolution neural network (CNN) has resulted in the improvement of the accuracy of land use land cover classification of hyperspectral satellite images (HSI) and also provided a new dimension to explore. This paper proposes a variant of the 3D-2D CNN Hybrid model to extract representational features from a different class of land use land cover using different receptive fields in a multi-stack arrangement. The proposed model focused on reducing the number of bands required for classification and training samples but on the other hand improving the diverse representational feature extraction. The paper also explores through experimentation the possible replacement of monotonic activation function ReLu using non-monotonic functions like Swish and Mish in 3D-2D CNN Hybrid models. The experiments are carried out using publically available HSI datasets with a special focus on small training datasets to establish the efficiency and robustness of the proposed model.

When the turning tool has worn and failed but the failure is not found, if it continues to be used for processing, it will break, and cause the workpiece to be scrapped, and even damage the machine tool. In order to avoid the loss caused by turning tool wear, the remaining useful life (RUL) prediction of turning tool wear has become a hot research topic in recent years. For RUL prediction in turning tools, the traditional machine is difficult to acquire sufficient degradation data and inconsistent data distribution among different turning tools in engineering, and they cannot provide better prediction accuracy to some extent. To solve the above problems, this paper proposes a multi-granularity feature extraction (MGFE) method based on the gray-level co-occurrence matrix (GLCM) and random forest (RF). Moreover, a health indicator (HI) of turning tools in the source domain was obtained. The common representative features in HI sequence of target domain was transferred to source domain and builds the condition monitoring and life prediction system of turning tools based on extreme learning machine and transfer learning. Finally, extreme vector machine (ELM) is used to construct the RUL prediction model. The research results show that the model constructed in this paper is effective in RUL prediction and can significantly improve the prediction accuracy of remaining useful life.

Rockburst is a typical dynamic phenomenon of mine destruction. With the expansion of mining scale and mining depth, its harm is becoming more and more serious. This has become an important problem to be solved urgently in the mining industry. This paper aims to study the prediction and prediction of rockburst risk based on particle swarm algorithm and neural network. This paper proposes a shock risk assessment method based on BP neural network. It uses existing shock pressure data to establish a regression model through BP network, and uses PSO algorithm to optimize connection weights to evaluate the slow convergence of BP network and easy to fall into local optimality. The shortcomings of and the degree of convergence was evaluated. In addition, this paper proposes a rockburst risk prediction method. In order to improve the accuracy of rockburst prediction, regional prevention and control measures and certain risk mitigation methods can also be quickly adopted. It not only identifies the mechanical properties of coal and rock mass in the laboratory, but also judges the possibility of rockbursts during mining. The experimental results in this paper show that 10 main factors that affect rockbursts are selected, 20 standard mechanical data sets are used, and a PSO-BP-based mine explosion risk assessment model is established, and the model is compared with the standard BP model Make a comparison. The results show that compared with the standard BP model, the evaluation accuracy of the PSO-BP model is increased by 15%. Finally, an example of mine risk assessment verifies the accuracy and overall applicability of the method.

In recent years, many researchers have used chaos maps to encrypt digital images due to their unpredictability, ergodicity, and sensitivity to initial values. This paper introduces a novel image encryption algorithm based on an integrated chaos map and bit-level diffusion technique. First, a novel multi-directional diffusion technique is applied to bit levels of the plain image. The innovative technique shifts bit levels of the plain image vertically and horizontally to eliminate visual information of the plain image. The proposed technique is so strong that is able to create high level of diffusion in just one round of implementation. Second, the integrated chaos map, which is a combination of Sine, Tent, and Logistic maps, is applied to the diffused image to encrypt the image. Also, for the objective of evaluating the performance of the proposed method, this paper presents new evaluation criteria, namely ClosenessNPCR and ClosenessUACI, in the field of number of pixel changing rate and unified average changed intensity, respectively. This paper proves that the novel evaluation criteria are more accurate than the preceding one, which is the mean of the achieved values. The implementation results show that the proposed image encryption scheme reaches a high security level, even more than preceding approaches.

The purpose of this paper is to compare the strategies of companies with data science practices and methodologies and the data specificities/variables that can influence the definition of a data science strategy in pharma companies. The current paper is an empirical study, and the research approach consists of verifying against a set of statistical tests the differences between companies with a data science strategy and companies without a data science strategy. We have designed a specific questionnaire and applied it to a sample of 280 pharma companies. The main findings are based on the analysis of these variables: overwhelming volume, managing unstructured data, data quality, availability of data, access rights to data, data ownership issues, cost of data, lack of pre-processing facilities, lack of technology, shortage of talent/skills, privacy concerns and regulatory risks, security, and difficulties of data portability regarding companies with a data science strategy and companies without a data science strategy. The paper offers an in-depth comparative analysis between companies with or without a data science strategy, and the key limitation is regarding the literature review as a consequence of the novelty of the theme; there is a lack of scientific studies regarding this specific aspect of data science. In terms of the practical business implications, an organization with a data science strategy will have better direction and management practices as the decision-making process is based on accurate and valuable data, but it needs data scientists skills to fulfil those goals. info:eu-repo/semantics/acceptedVersion

At present, the mortgage loan of farmland contractual management right is in the pilot and exploration stage. In this overall environment, how to formulate an appropriate pricing model according to the particularity of farmland property right and the actual situation is the theoretical support to be solved. On the basis of theoretical analysis, model construction and analysis of existing problems, this paper establishes a binary tree pricing method of farmland management right mortgage based on machine learning and complex network algorithm. This paper analyzes the basic theory of rural land management right mortgage pricing and constructs the pricing model. Based on the Markov decision process model of dynamic pricing problem, this paper proposes the solution algorithm and proposes the dynamic pricing solution for this paper from two aspects of value function and strategy gradient reinforcement learning algorithm. This paper analyzes the basic principle of A3C algorithm and expounds the algorithm design and neural network architecture for the specific dynamic pricing problem in this paper. The dynamic pricing method of rural land mortgage based on deep reinforcement learning designed in this paper can well predict the real price of rural land management right mortgage pricing and effectively optimize the mortgage loan environment of rural contracted land management right, which is the innovation of financial system in the current new rural construction.

The construction of risk knowledge graphs aims at the effective organization and utilization of enterprise knowledge resources in big data environments. To address the problem of static mapping in existing enterprise knowledge graphs, this paper introduces the time dimension to describe the evolutionary characteristics of enterprise risk events, such as dynamics, suddenness and timeliness. Through information extraction, knowledge fusion, ontology construction and dynamic knowledge reasoning about risk knowledge, a bottom-up enterprise dynamic risk knowledge graph is systematically constructed. In the knowledge fusion link, aiming at the imbalanced classification problem for the entity samples of a data set, this paper proposes the ResNet dynamic knowledge reasoning method to improve the loss balance function of the Multi-Net model. The experiments show that the new model can effectively improve the accuracy of entity and relationship prediction. Finally, the knowledge graph is applied to an intelligent question-answering system.

Deep neural networks (DNNs) have evolved as a beneficial machine learning method that has been successfully used in various applications. Currently, DNN is a superior technique of extracting information from massive sets of data in a self-organized method. DNNs have different structures and parameters, which are usually produced for particular applications. Nevertheless, the training procedures of DNNs can be protracted depending on the given application and the size of the training set. Further, determining the most precise and practical structure of a deep learning method in a reasonable time is a possible problem related to this procedure. Meta-heuristics techniques, such as swarm intelligence (SI) and evolutionary computing (EC), represent optimization frames with specific theories and objective functions. These methods are adjustable and have been demonstrated their effectiveness in various applications; hence, they can optimize the DNNs models. This paper presents a comprehensive survey of the recent optimization methods (i.e., SI and EC) employed to enhance DNNs performance on various tasks. This paper also analyzes the importance of optimization methods in generating the optimal hyper-parameters and structures of DNNs in taking into consideration massive-scale data. Finally, several potential directions that still need improvements and open problems in evolutionary DNNs are identified.

To create a safe and secure cyberspace, many researchers have created and proposed Intrusion Detection Systems (IDSs). Different types of IDSs are either designed to address only a single kind of intrusion or multiple variants. In this paper, we proposed a new context-aware feature extraction method as a pre-processing step for Convolutional Neural Network (CNN)-based multiclass intrusion detection. Feature selection is also used to reduce the feature space and classification time. For attack-type classification, we used CNN which is generally well-known for its better classification ability on image recognition tasks. We have exploited this ability to develop an IDS that can identify different types of intrusions ranging from 4 to 12 types. In our study, we evaluated our proposed Context-aware Feature Extraction-based CNN IDS on different datasets with multiple classes where it was able to successfully improve classification accuracy compared to the models with no preprocessing steps and other existing methods. We carried out the performance evaluation and comparison using four different datasets, NSL-KDD, CICIDS2017, ADFA-LD, and ADFA-WD. These datasets have either host-based or network-based features, which is another area that we investigated in this paper.

Most super-resolution (SR) methods proposed to date do not use real ground-truth high-resolution (HR) and low-resolution (LR) image pairs; instead, the vast majority of methods use synthetic LR images generated from the HR images. This approach yields excellent performance on synthetic datasets, but on real-world poor quality surveillance video footage, they suffer from performance degradation. A promising alternative is to apply recent advances in style transfer for unpaired datasets, but state-of-the-art work along these lines has used LR images and HR images from completely different datasets, introducing more variation between the HR and LR domains than necessary. In this paper, we propose methods that overcome both of these shortcomings, applying unpaired style transfer learning methods to face SR but using HR and LR datasets that share important properties. The key is to acquire roughly paired training data from a high-quality main stream and a lower-quality sub-stream of the same IP camera. Based on this principle, we have constructed four datasets comprising more than 400 people, with 1–15 weakly aligned real HR–LR pairs for each subject. We adopt a cycle generative adversarial networks (Cycle GANs) approach that produces impressive super-resolved images for low-quality test images never seen during training. Experiments prove the efficacy of the method. The approach to face SR advocated for in this paper makes possible many real-world applications requiring the extraction of high-quality face images from low-resolution video streams such as those produced by security cameras. Developers of diverse applications such as face recognition, 3D face reconstruction, face alignment, face parsing, human–computer interaction, remote sensing, and access control will benefit from the methods introduced in this work.

In recent years, with the change of lifestyle in Europe and America, the incidence of breast cancer in Chinese women is increasing. In order to find the model of breast cancer image screening and diagnosis with higher accuracy and better classification performance, this paper mainly constructs the breast cancer CT image detection model and the breast cancer screening model based on the convolution and deconvolution neural network (CDNN) through the convolution neural network (CNN). In this paper, the fuzzy C-means clustering algorithm (FCM) is used to improve and optimize the image of breast cancer, and the experimental results are analyzed. The optimized kernel fuzzy C-means clustering algorithm was tested on a common dataset to segment the region of interest more accurately. Our experiments show that the new deep learning model of this paper improves the automatic classification performance of breast cancer. In this paper, the research results of deep learning are applied to the medical field, and a new method based on CNN model for breast cancer screening and diagnosis is proposed, which provides a new idea for improving the artificial intelligence assisted medical diagnosis method.

Traditional observation methods of the boundary layer are susceptible to external factors. In particular, detection data are relatively scarce in special areas such as plateaus and oceans. However, occultation observation data have the unique advantage of global coverage, and the boundary layer information of the occultation profile is rich. Based on the machine learning algorithm, this paper combines GPS occultation technology to improve the algorithm and constructs the boundary layer height simulation model based on the actual situation and analyzes its functional structure one by one. Moreover, in order to verify the validity of the simulation model, a simulation analysis is performed in combination with actual data. In addition, the performance of the model is verified from multiple aspects, and the results of the research are calculated by mathematical statistics, and the corresponding statistical diagram is drawn. Through experimental analysis, it can be known that the model constructed in this paper can effectively simulate the boundary height and has certain practical effects.

How to build a football match prediction model and use scientific methods to solve the prediction problem has become a key point in the application of artificial intelligence in the sports industry. In this paper, we choose a BP neural network model that is powerful in processing nonlinear data to perform research. According to the demand, this paper constructs a gray fuzzy prediction model based on neural network, a gray extreme learning machine prediction model, and a gray fuzzy extreme learning machine prediction combination model based on neural network. Moreover, this paper tests the neural network model by comparing actual results with predicted results. In addition, by predicting and analyzing the football league data, this article tests the three models in terms of match result prediction accuracy, data processing speed, data transmission accuracy, match analysis scores, etc., and uses statistical analysis methods to process data, and uses intuitive statistical graphs to obtain the processing results. The research results show that the gray fuzzy extreme learning machine prediction combination model based on neural network constructed in this paper can retain the advantages of a single model and effectively improve the prediction accuracy of the model and the performance of the system.

The stable operation of intelligent robots requires the effective support of machine vision technology. In order to improve the effect of robot machine vision recognition, based on deep learning, this paper, under the guidance of machine learning ideas, proposes a target detection framework that combines target recognition and target tracking based on the efficiency advantages of the KCF visual tracking algorithm. Moreover, this paper designs a vision system based on a high-resolution color camera and TOF depth camera. In addition, by modeling the coordinate conversion relationship of the same object in the camera coordinate system of two cameras, the projection relationship of the depth map collected by the TOF camera to the pixel coordinate system of the high-resolution color camera is determined. In addition, this paper designs experiments to verify the performance of the model. The research results show that the method proposed in this paper has a certain effect.

In order to overcome the shortcomings of the current English network learning system, based on the neural network algorithm, this paper constructs an intelligent English network learning system based on the improved algorithm. Moreover, by analyzing the coupling between recurrent neural networks by contrast methods, this paper infers the coupling between recurrent neural networks. Moreover, this paper studies the continuous attractors of the autoencoder neural network and studies the continuous attractors of different types of autoencoder models. On this basis, this paper expands the existing model, adds the module of the interaction between the external input and the visible layer and studies the conditions required for the continuous attractor of the autoencoder model. In addition, on the basis of actual needs, this paper constructs the basic structure of the model and integrates it into the improved algorithm proposed in this paper to realize English online intelligent learning. Finally, this paper designs experiments to analyze the practical effects of this model and analyzes the experimental results through mathematical statistics. The research results show that the English network learning system constructed in this paper is effective.

The increase in the size of the city and the increase in population mobility have greatly increased the number of vehicles on the road, and at the same time brought considerable challenges to the traffic management department. In recent years, more and more experts and scholars have devoted themselves to applying sensors, network communication and dynamic adaptive technologies to road traffic management systems. At present, people have not completely overcome all kinds of complex problems in traffic supervision. The complexity of traffic information and the defects of identification algorithms have brought great challenges to intelligent traffic management. This article has launched a research on the intelligent Internet of Things traffic management system, with the detection and recognition of stationary vehicles and seat belts as the key analysis targets. When monitoring stationary vehicles, this paper replaces the background difference algorithm commonly used in dynamic vehicle detection with a new recognition algorithm. From the experimental results, the average detection accuracy of the new algorithm is 96.77% higher than the previous 87.56%. When studying the driver's seat belt detection, this paper combines the YOLOv3 target detection algorithm and the lightweight network structure, and proposes a driver-oriented positioning algorithm. With the increase in the number of lightweight templates, the accuracy of the positioning algorithm has increased from 80.57 to 99.98%. But on the other hand, the detection speed has also changed from 78 to 69 frames/s.

The goal of steganalysis is to unearth a concealed message hidden inside an innocent carrier by steganography. Steganography in the hands of unlawful people can pose a great threat to society. Secret message is embedded as a noise (residue) which silently disrupts the statistical nature of the carrier without visual transformation. For the purpose of unearthing covert communication, modeling this noise (residue) is a crucial factor. In this paper, a hybrid deep learning framework is proposed with convolutional neural network (CNN) to emphasize the need for residual based investigation for digital image steganalysis. In order to model the noise residuals, five types of handcrafted features are extracted, in which the first four types rely on acquiring noise residuals based on filtering by linear and nonlinear filters, and the fifth type relies on residual acquisition method based on Empirical Mode Decomposition (EMD). The extracted features are categorized using a robust CNN with a new parallel architecture that is capable of learning intricate details from input features to classify it as cover or stego. Mostly CNNs are trained with raw images, but in the proposed method, the 1-dimensional residual features are stacked into 2-dimensional grid and are then used to train the CNN. Three spatial content-adaptive and four spatial non-content-adaptive algorithms are used to evaluate the performance of the proposed architecture. The experimental results show the versatility and robustness of the proposed hybrid architecture towards these algorithms when compared to existing state-of-the-art steganalytic methods. A practical issue prevalent in deploying steganalysis in real-world is ‘mismatch scenario,’ and based on the experimentation done in this paper, the proposed architecture performs well under stego algorithm mismatch and payload mismatch scenarios.

In order to improve the effect of modern music teaching, this paper builds an intelligent music teaching system based on machine learning and SVM algorithm, innovates the music teaching process, and gradually expands from the simplest three-layer structure BPNN to a multi-layer structure. Moreover, this paper proposes a method of dividing the error by the proportion of each link's contribution to the error, and the idea that the error of the hidden layer node is the sum of the errors on each link during the forward propagation process. In addition, this paper combines the actual needs of music teaching to construct an intelligent music teaching system. Finally, this paper conducts training tests on music teaching data and sets up the experimental group and the control group to evaluate the system teaching effect based on actual needs. The research results show that the performance of the intelligent music teaching system constructed in this paper is good.

The operation of the mobile interactive autonomous learning system injects advanced management technology and scientific and reasonable management system for the effective management and arrangement of the school's teaching, enables students to conduct autonomous learning in their spare time, makes full use of students' fragmented time, and improves students' learning enthusiasm and efficiency. Based on the neural network algorithm, this paper constructs an English network learning interactive evaluation model, studies the influence of the flattening layer in the convolutional neural network structure on the structural complexity, and then proposes spatial pyramid weighted average pooling to optimize the traditional flattened layer. Moreover, this paper evaluates RSPP from three aspects: space complexity, training time-consuming, and accuracy. In addition, this paper designs two types of integrated convolutional neural networks, namely Bagging integration and snapshot integration. Finally, this paper evaluates the performance of the model through experiments and counts the experimental results. The research results show that the model constructed in this paper has a certain effect.

Providing of energy is one of the most important issues for each country. Also, environmental issues due to fossil fuel depletion are other serious concern of them. In this regard, moving toward energy sustainability is a constructive solution for each country. This paper studies the short-term planning of generating units in renewable energy-based distribution networks equipped with plug-in electric vehicles (PEVs). PEVs can cause problems for distributed energy sources in the electrical grid, as well as power units inside the grid. So, to overcome this problem, an efficient stochastic programming technique is designed to allow the control entity to control the charging behavior of PEVs for managing power units. In this paper, to obtain the least total cost, a new method is suggested to decrease the reliability expenses. In other words, the vehicle-2-grid (V2G) is applied to decrease the operating. On the other hand, a novel stochastic flow using the unscented transform is suggested to improve the model of the severe uncertainty due to the wind power, photovoltaic (PV) and charging/discharging power of PEVs. In this research work, a novel and efficient optimization algorithm called ‘θ-modified krill herd (θ-MKH)” is used as an applicable technique to optimize the microgrid (MG) operation. This algorithm is useful and has many advantages like the runaway from the local optima with fast converging in comparison with other methods. Also, the satisfactory efficiency of the suggested randomized manner is validated on an MG connected to the main grid.

Deep neural network is an important computer operating system in China. It has made great breakthroughs in target recognition, image classification and other fields. It plays a key role in multi-system integration and intelligent manufacturing industry, such as training and testing. The purpose of this paper is to study the multi-system fusion of deep neural network and its application in intelligent manufacturing industry. By setting up experiments, the multi-system fusion of neural network is carried out, combining with big data and artificial intelligence to verify the efficient operation of neural network in multi-system fusion. Using the methods of mathematical analysis and big data fitting, the collected data are classified, the experimental data are collected and then analyzed. In this paper, the reliability of this method is verified by research; the application of multi-system fusion based on deep neural network in intelligent manufacturing industry can effectively integrate all systems, improve the comprehensive working efficiency of each system by about 20% and improve the multi-system fusion of deep neural network and its application in intelligent manufacturing industry by about 15%. Thus, as the terminal of the system, the deep neural network plays the leading role of multiple systems. It can effectively integrate the various systems and improve the comprehensive work efficiency of each system, which has guiding significance for the development of industry.

In order to improve the marketing effect of e-commerce products, based on machine learning algorithms, this paper constructs an e-commerce product marketing model based on machine learning and SVM. Moreover, this paper studies the classic reinforcement learning algorithm Q-learning and proposes an improved Q-learning algorithm. In addition, this paper uses the method of mean standardization to reduce the noise impact of the reward signal caused by the unfixed time interval between decision points, further constructs a standardization factor for the deviation caused by the asynchronous update of the time interval in the iterative process of the Q value function and updates the standardization factor according to the update method of the value function, and proposes the Interval-Q algorithm. At the same time, in view of the fact that traditional reinforcement learning algorithms cannot effectively deal with the observable part of customer status in direct marketing scenarios, based on the deep reinforcement learning DQN model, this paper combines with the idea of hybrid model to propose a DQN model based on dual networks. Finally, this paper uses public data sets for model training and simulation environment construction and then evaluates the algorithm proposed in this paper from different angles and analyses model performance based on examples. From the research results, it can be seen that the precision marketing model constructed in this paper has a good effect and can be applied to practice.

Fire smoke detection in forest faces much more challenges than in local areas or indoors. Conventional fire smoke methods using static features extracted form single image directly cannot handle some disturbed factors exist in forest, such as shaking trees and fog/haze. On the other hand, it is difficult to capture the dynamic features of fire smoke while they are vital for fire smoke detection. This paper proposes an effective method of extracting features based on sequential images for smoke detection, quasi-dynamic features are extracted using on pixel-block arranged image sets. First, consecutive frames are rearranged into a new big image based on a pixel-block rule, so that the new image still keep the whole structure of original image on block level, and the change of different pixels in the same block, which comes from the same position of each frame, can reflect the dynamic features by special process. Second, to process the new arranged big image, driven by single image wavelet transform for denoting local signal characteristics, Dual Tree-Complex Wavelet Transform is utilized to decompose the new big image into eight images with the same size of the source image after several level-decomposition, including four directions (HH, HL, LH, LL) with two decomposed images in each direction, so that the changes from smoke in different orientation can be extracted and depicted in these subbands. Third, a multi-scale dictionary learning method is proposed to learn dictionaries of each group images. Furthermore, elastic net is introduced for sparse coding and feature coefficients extraction. All operations above contribute to a significant improvement for smoke detection in this paper. Extensive experiments are performed to validate the effectiveness of the proposed approach.

In-depth discussion and research on the credit issues of the logistics industry are not only of vital significance to the in-depth development of the logistics industry, but also have a significant impact on the sustainable development of the entire logistics industry and even the Chinese economy. This paper combines machine learning algorithms to improve the neural network and builds a credit system for the smart logistics public information platform. When studying the credit evaluation index system of logistics enterprises, the majority of logistics consumers are used as the evaluation subject, and the logistics users are surveyed, and the initial index system established is scored. Then, the method of factor analysis is used to sort and analyze the results of the questionnaire and determine the final evaluation index. In addition, according to the development of logistics enterprises themselves, this paper uses the analytic hierarchy process to evaluate the credit ratings of logistics enterprises from the perspectives of logistics enterprise customers and managers. This will be more authentic and convincing for the evaluation results.

Automatic text recognition system might serve as an important factor in creating a paperless environment through digitizing and processing the existing paper documents in the upcoming days. Handwritten recognition using deep learning methods has been widely explored by many researchers. The existence of large quantity of data and a variety of algorithmic innovations enable the ease of training deep neural networks. Different techniques have been initiated in the literature for recognizing text from handwritten documents. This paper proposes a hybrid handwritten text recognition (H2TR) model using deep neural networks that use the sequence-to-sequence (Seq2Seq) approach. This hybrid model makes use of the salient features of convolution neural network (CNN) and recurrent neural network (RNN) with long–short-term memory network (LSTM). It uses CNN to extract the features from the handwritten image. The features that are extracted are later modelled with a sequence-to-sequence approach and fed to RNN–LSTM for encoding the visual features and decoding the sequence of letters that are available in the handwritten image. The proposed model is tested with IAM and RIMES handwritten databases, which shows competitive letter accuracy and word accuracy results.

The work in this paper is based on an industrial debutanizer column in a petroleum refinery located in Malaysia, which produces LPG (liquefied petroleum gas) as the top stream and light naphtha as the bottom stream. The controlled outputs, which are the critical product quality to be measured, are the concentrations of the top and the bottom streams. It is required to maintain the product quality for profitability, and recent trends in soft-computing have seen a plethora of methods developed for this purpose. However, due to practical constraints experienced by the plant that limit extensive plant step tests, data available for the development of the soft sensor for this industrial debutanizer column is scarce. Hence, in this paper, a neuro-fuzzy technique (ANFIS) is investigated and compared against the widely used ANN model for the special case of limited training data samples of the industrial debutanizer column. It is observed that in comparison to ANN, ANFIS has better generalization performance and can work well with limited training data samples. From the results, it was observed that the prediction performance of the ANFIS model generally improved the RMSE by approximately 10 times in comparison to that of ANN.

Traditional aerobics gesture recognition has shortcomings such as low scalability, limitations in application scenarios, limitations in labor costs, and human–computer interaction. In order to improve the efficiency of aerobics posture recognition, based on neural network, this paper constructs aerobics posture recognition model combined with sensor network. Moreover, aiming at the unsatisfactory performance of the natural feature-based visual 3D registration method for scenes with sparse texture features and complex dynamic scenes, a deep neural network based on CNN + LSTM is proposed to establish the relative motion relationship between camera positions in continuous video sequences. In addition, this paper uses the transfer learning method to apply the network training parameters for the classification task to the video sequence posture recognition in this paper. Finally, considering the temporal correlation between video sequences, this paper uses the LSTM structure to store long-term image memory information. The experimental results show that the performance of the model constructed in this paper is good.

Economic data include data of various types and characteristics such as macro-data, meso-data, and micro-data. The source of economic data can be the data related to economy held by the National Bureau of statistics and a various software. These multi-source and heterogeneous data have important value for economic analysis and forecasting. Taking into account the limitations of existing methods such as low accuracy and complex calculations, this paper proposes an economic data analysis and prediction method based on machine learning. We use machine learning to solve the data fusion problem in the process of multi-source data analysis and prediction in the economic field. Specifically, we proposes an economic data analysis and forecasting method combining convolutional auto-encoder and extreme gradient boosting algorithms. This method uses a convolutional auto-encoder to extract the data characteristics of the normalized parameter sequence and uses it to train an extreme gradient boosting model to predict the level of economic development and evaluate the importance of each influencing factor. Finally, through a case study, this paper integrates the data of labor force, education and population to forecast GDP. Through the verification of this case, the prediction accuracy of the proposed method is higher than the AE-XGBoost method and CAE-1D-XGBoost method used in this experiment, and the error is kept below 11.7%.

This paper aims to study the actual utility of real estate pricing models based on data mining and machine learning. In order to achieve this goal, this paper introduces appropriate trend estimation methods, adjusts pricing models and processes, and realizes trend estimation that changes over time to make the resulting pricing model have advantages such as dynamics, accuracy, and flexibility over the original model. Moreover, this paper proposes a real estate pricing model based on the quadratic exponential smoothing time-varying trend estimation. In addition, this paper uses the quadratic exponential smoothing method to calculate the index trend in the random process of the house price index, and performs segmentation processing on the pricing model according to the index cycle, so as to obtain the real estate pricing method under the time-varying trend. Finally, this paper adjusts the volatility parameters and the mean recovery rate to time-varying piecewise functions, uses the quadratic variation to calculate the volatility parameters and the martingale valuation method to calculate the mean recovery rate parameters, and establishes the real estate pricing model of the time-varying O–U process. Case studies show that the model constructed in this paper has good performance and has certain practical effects.

Face recognition applications focus on local features to prevent detailed information from being omitted while the feature extraction processes. This paper is based on presenting a local pattern-based model to extract more discriminative features that lead to more accurate classification. In local pattern-based feature extraction, the LBP is one of the most important approaches that many variants of this method have been proposed till now. LBP calculation is based on differences between the central pixel and the desired one. In contrast, the information hidden in the selected pixel’s neighborhood pixels is not included in this process. This paper proposes the DR_LBP approach to address this failure by defining distances and using some of them in a ratio form. Successful results have been earned in many experimental results. In LBP, the calculations’ primary flow takes advantage of two pixels in the LBP box, the central and the desired pixel. Contrary to the original LBP, this paper’s proposed approach uses three pixels of LBP box to conduct the feature vector, which leads to employing the information hidden in the relationship between neighboring pixels. This approach applies the experiments on two standard datasets, ORL Yale face and Faces94 dataset. The accuracy percent of the proposed plan is 95.95, 94.09 and 98.01 on ORL, Yale face and Faces94 dataset, respectively, which is the reason to present this model as a new face feature extraction approach.

The introduction of logistics theory and logistics technology has made the government and enterprises gradually realize that the development of logistics has an important strategic role, which can effectively solve the changing needs of users, optimize resource allocation, improve the investment environment, and enhance the overall strength and overall competitiveness of the regional economy. This paper carries out matrix–vector multiplication operations and weight update operations, designs a perceptron neural network model, and realizes a simulation platform based on MLP neural network. Moreover, on the basis of the standard MLP neural network, this paper proposes to use the deep learning training mechanism to improve the MLP neural network, which provides effective technical support for the improvement of the prediction model. In addition, through the fusion of deep learning and MLP neural network, an MLP neural network with three hidden layers is determined. Finally, this paper builds a model based on the MLP neural network algorithm, selects the RBF kernel function as the kernel function of the model by referring to the relevant literature, and uses PSO to optimize the combination of parameters. It can be seen from the result of the evaluation index that each evaluation index is relatively small. The result shows that the prediction is accurate, and the empirical result shows the feasibility of the model to predict the demand for industrial logistics in Shanxi Province.

With the increasing number of software applications that allow altering digital images and their ease of use, they weaken the credibility of an image. This problem, together with the ease of distributing information through the Internet (blogs, social networks, etc.), has led to a tendency for information to be accepted as true without its veracity being questioned. Image counterfeiting has become a major threat to the credibility of the information. To deal with this threat, forensic image analysis is aimed at detecting and locating image forgeries using multiple clues that allows it to determine the veracity or otherwise of an image. In this paper, we present a method for the authentication of images. The proposed method performs detection of copy-move alterations within an image, using the discrete cosine transform. The characteristics obtained from these coefficients allow us to obtain transfer vectors, which are grouped together. Through the use of a tolerance threshold, it is possible to determine whether there are regions copied and pasted within the analysed image. The results obtained from the experiments reported in this paper demonstrate the effectiveness of the proposed method. For the evaluation of the proposed methods, experiments were carried out with public databases of falsified images that are widely used in the literature.

Medical image fusion techniques can further improve the accuracy and time efficiency of clinical diagnosis by obtaining comprehensive salient features and detail information from medical images of different modalities. We propose a novel medical image fusion algorithm based on deep convolutional generative adversarial network and dense block models, which is used to generate fusion images with rich information. Specifically, this network architecture integrates two modules: an image generator module based on dense block and encoder–decoder and a discriminator module. In this paper, we use the encoder network to extract the image features, process the features using fusion rule based on the Lmax norm, and use it as the input of the decoder network to obtain the final fusion image. This method can overcome the weaknesses of the active layer measurement by manual design in the traditional methods and can process the information of the intermediate layer according to the dense blocks to avoid the loss of information. Besides, this paper uses detail loss and structural similarity loss to construct the loss function, which is used to improve the extraction ability of target information and edge detail information related to images. Experiments on the public clinical diagnostic medical image dataset show that the proposed algorithm not only has excellent detail preserve characteristics but also can suppress the artificial effects. The experiment results are better than other comparison methods in different types of evaluation.

The knee joint is the largest and most complex flexion and extension joint of the human body. It supports most of the weight of the human body during the whole body during standing or exercise. Because the knee joint has the characteristics of complex structure and large load, it is also vulnerable to damage. An effective diagnosis in the early stage of injury or lesion of the knee joint is of great help to the later treatment. At present, the commonly used knee joint examination methods have the problems of large trauma and high cost. Therefore, this paper uses machine learning technology to study the classification algorithm of knee joint vibration signal. The research results of this paper were verified by selecting the subjects to form a healthy group and a disease injury group. The experimental results show that the proposed signal denoising algorithm is superior to the traditional denoising algorithm. After analyzing several classification algorithms, the multi-classifier fusion algorithm has excellent performance in signal classification. The experimental results show that the research results can be applied to the classification of knee joint vibration signals, and then applied to the clinical diagnosis of knee joint diseases.

The improvement of object detection performance mainly depends on the extraction of local information near the target area of interest, which is also the main reason for the lack of feature semantic information. Considering the importance of scene and semantic information for visual recognition, in this paper, the improvement of the object detection algorithm is realized from three parts. Firstly, the basic residual convolution module is fused with the separable convolution module to construct a depth-wise separable convolution network (D_SCNet-127 R-CNN). Then, the feature map is sent to the scene-level region proposal self-attention network to re-identify the candidate area. This part is composed of three parallel branches: semantic segmentation module, region proposal network, and region proposal self-attention module. Finally, this paper uses deep reinforcement learning combined with a border regression network to achieve precise location of the object, and improve the calculation speed of the entire model through a light-weight head network. This model can effectively solve the limitation of feature extraction in traditional object detection and obtain more comprehensive detailed features. The experimental on MSCOCO17, Pascal VOC07, and Cityscapes datasets shows that the proposed method has good validity and scalability.

Source localization with a network of low-cost motes with limited processing, memory, and energy resources is considered in this paper. The state-of-the-art methods are mostly based on complicated signal processing approaches in which motes send their (processed) data to a fusion center (FC) wherein the source is localized. These methods are resource-demanding and mostly do not meet the limitations of motes and network. In this paper, we consider distributed detection where each mote performs a binary hypothesis test to detect locally the existence of a desired source and sends its (potentially erroneous) decision to FC during just one bit (1 indicates source existence and 0 otherwise). Hence, both processing and bandwidth constraints are met. We propose to use an artificial neural network (ANN) to correct erroneous local decisions. After error correction, the region affected by the source is specified by nodes with decision 1. Moreover, we propose to localize the source by deep learning in FC which converts the network of decisions 1 and 0 to a black and white image with white pixels in the locations of motes with decision 1. The proposed schemes of error correction by ANN (ECANN) and source localization with deep learning (SoLDeL) were evaluated in a fire detection application. We showed that SoLDeL performs appropriately and scales well into large networks. Moreover, the applicability of ECANN in delineation of farm management zones was illustrated.

Multi-access edge computing (MEC) is emerging as a new and promising methodology with the development of Internet of Things (IoT) and smart devices, which enables a large class of applications and has emerged with a significance to change our life, and also is raising the challenging research issues due to the requirements of low latency, deployment independence, location awareness and mobility support. However, recent advances on distributed artificial intelligence (AI), big data, and edge/terminal cooperation schemes show that IoT still struggles with fundamental, long-standing problems, such as computational models, resource allocation and scheduling, power efficient data processing and cooperative decision-making mechanisms in edge. How to enhance IoT with MEC, distributed AI, cooperation and novel applications is worth exploring. The objective of this special issue is to report high-quality state-of-the-art research contributions that address these key aspects of MEC-enabled IoT and novel applications. By presenting a selection of papers on various topics related to MEC-enabled IoT, we hope to shed light on the multiple aspects of this emerging paradigm. The papers included in this issue propose solutions for resource management and allocation, multimedia processing, as well as novel applications.

Marine object detection is an appealing but challengeable task in computer vision. Even though recent popular object detection algorithms perform well on common classes, they cannot acquire satisfied detection performance on marine objects because underwater images are affected by color cast and blur, and scales of the target in underwater images are usually small. These phenomena aggravate the difficulty of detection. Thus, it is urgent to design a proper structure to settle marine object detection issues. To this end, this paper proposes a novel scale-aware feature pyramid architecture named SA-FPN to extract abundant robust features on underwater images and improve the performance on marine object detection. Specifically, we design a special backbone subnetwork to improve the ability of feature extraction, which could provide richer fine-grained features for small object detection. What is more, this paper proposes a multi-scale feature pyramid to enrich the semantic features for prediction. Each feature map is enhanced by the higher level layer with context information through a top-down upsampling pathway. Through obtaining ample feature maps on underwater images, our algorithm could generate multiple bounding boxes for each target. To mitigate the reduplicative boxes and avoid miss suppression, we replace the non-maximum suppression method with soft non-maximum suppression. In this paper, we evaluate our algorithm on underwater image datasets and achieve 76.27% mAP. Meanwhile, we conduct experiments on PASCAL VOC datasets and smart unmanned vending machines datasets and get 79.13% mAP and 91.81% mAP, respectively. The experimental results reveal that our approach achieves best performance not only on marine object detection, but also on common classes.

The tremendous growth of services available on the Internet makes user profiling an increasing important topic in web personalization. While profiling a user, one of the main challenges is that user preferences and interests usually change over time. It would be much appreciated, if the user profile could describe these changes. Such user profile is defined as time-aware user profile (TUP) in this paper. The TUP can delineate both dynamic user preferences and interests and evolutions of them, which illustrates that it can represent users more clearly and accurately. A TUP consists of a set of time slot-specific user profiles, which is defined as sub-time-aware user profile (sTUP). And a TUP is special for a user; then, its sTUPs separately represent preferences and interests of this user for different time slots. Constructing a TUP needs the constructions of its sTUPs. While constructing a sTUP from the user behavior logs for a time slot, in this paper, we present a novel learning model called personal service ecosystem (PSE) to delineate user preferences and interests naturally. Different from PSE, sTUP is the representation model. For a time slot, the sTUP is constructed based on the PSE recovered from the user behavior logs of this time slot. In terms of a TUP, two main approaches to analyze the evolutions of sTUPs in this TUP are further discussed. They are the evolution analysis of various margins between every two neighboring sTUPs called EA-VM and the evolution analysis of different sTUPs on raw data defined as EA-RD. EA-VM mainly focuses on the fine-grained evolution between two neighboring time slots by analyzing these various margins. It can be further divided into the clustering method and the distribution analysis approach. EA-RD chiefly pays attentions to the overall evolution of such sTUPs. By a comprehensive survey on the raw data of sTUPs, we summarize six interesting overall evolution patterns, including refugee pattern, periodic pattern, stable pattern, fluctuant pattern, emergency pattern and zombie pattern. Eventually, a systematic empirical study based on our collection data has been conducted, where smartphone users are taken as examples to illustrate our proposed models and approaches. And experimental results highlight the superiority of these approaches.

The human attention span is continuously decreasing, and the amount of time a person wants to spend on reading is declining at an alarming rate. Therefore, it is imperative to provide a quick glance of important news by generating a concise summary of the prominent news article, along with the most intuitive headline in line with the summary. When humans produce summaries of documents, they not only extract phrases and concatenate them but also produce new grammatical phrases or sentences that coincide with each other and capture the most significant information of the original article. Humans have an incredible ability to create abstractions; however, automatic summarization is a challenging problem. This paper aims to develop an end-to-end methodology that can generate brief summaries and crisp headlines that can capture the attention of readers and convey a significant amount of relevant information. In this paper, we propose a novel methodology known as SHEG, which is designed as a hybrid model. It works by integrating both extractive and abstractive mechanisms using a pipelined approach to produce a concise summary, which is then used for headline generation. Experiments were performed on publicly available datasets, viz. CNN/Daily Mail, Gigaword, and NEWSROOM. The results obtained validate our approach and demonstrate that the proposed SHEG model is effectively producing a concise summary as well as a captivating and fitting headline.

The work in this paper presents a MTS from Sanskrit to English language using a hybridized form of direct and rule-based machine translation technique. This paper also discusses the language divergence among Sanskrit and English languages with a recommended solution to handle the divergence. The proposed system has used two bilingual dictionaries (Sanskrit–English, Sanskrit–UNL), a tagged Sanskrit corpus, a Sanskrit analysis rule base and an ELGR base. Elasticsearch technique has enhanced the translation speed of the proposed system for accessing the data from different data dictionaries and rule bases used for the system development. The system uses CFG in CNF for Sanskrit language processing and CYK parsing technique for processing the input Sanskrit sentence. This work also presents a novel algorithm which creates a parse tree from the parsing table. ELGR base and bilingual dictionaries generate the target language sentence. The proposed system is evaluated using natural language toolkit API in python and achieved a BLEU score of 0.7606, fluency score of 3.63 and adequacy score of 3.72. A comparison of the proposed system with state-of-the-art systems shows that the proposed system outperforms existing systems.

The purpose of smart city is to enhance the optimal utilization of scarce resources and improve the resident’s quality of live. The smart cities employed Internet of Things (IoT) to create a sustainable urban life. The IoT devices such as sensors, actuators, and smartphones in the smart cities generate data. The data generated from the smart cities are subjected to analytics to gain insight and discover new knowledge for improving the efficiency and effectiveness of the smart cities. Recently, the application of deep learning in smart cities has gained a tremendous attention from the research community. However, despite raise in popularity and achievements made by deep learning in solving problems in smart cities, no survey has been dedicated mainly on the application of deep learning in smart cities to show recent progress and direction for future development. To bridge this gap, this paper proposes to conduct a dedicated survey on the applications of deep learning in smart cities. In this paper, recent progress, new taxonomies, challenges and opportunities for future research opportunities on the application of deep learning in smart cities have been unveiled. The paper can provide opportunities for experts in the research community to propose a novel approach for developing the research area. On the other hand, new researchers interested in the research area can use the paper as an entry point.

Electricity, a kind of clean energy, has been widely used in people’s production and daily life. However, it is very difficult to estimate the electricity energy production in advance and store the rest of the electric energy due to the climate, environment, population and other factors. Based on data preprocessing and artificial intelligence optimization algorithm, this paper introduces a combined forecasting method. The proposed method contains six individual methods, and each individual method has its own usage. Singular spectrum analysis (SSA) is adopted to reduce noise from the original data; three individual forecasting methods, Jordan neural network, the echo state network, least squares support vector machine, are applied to obtain the intermediate forecasting results; two optimization algorithms, particle swarm optimization and simulated annealing, are used to optimize the parameters of the combined model. This paper not only validates the superiority of the combined model compared to the single predictive model through the simulation experiments of power load data and electricity price data. The mean absolute percent error (MAPE) of the combined power load and electricity price forecast results are 1.14% and 7.58%, respectively, which are higher than the MAPE error of the corresponding single models prediction results. It has also been verified that the process of eliminating noise by the SSA plays a positive role in the accuracy of the combined forecasting model. In addition, two series of experiments on the power load data lead to two very interesting conclusions. One of the conclusions is that as the size of the test data increases, the prediction accuracy of the model decreases; the other is that the predicted result calculated through the optimized combined weight is better than the combined result calculated using the average weight, and the average weight is used. Weighted combination does not improve the prediction accuracy of a single model.

In order to realize the terminal optical element online detection system in the Shenguang III system, each optical element in each terminal optical component in the target room is detected. The research on the optical damage of terminal optical components focuses on the search for damage points, the extraction of damage information, and the classification of damage types. In addition, damage classification and identification of terminal optical components are performed through machine learning, and infrared nondestructive testing is used as technical support to improve the identification model and reduce the complexity of the spectral model. After studying the preprocessing and dimensionality reduction methods of near-infrared spectroscopy, this paper compares the effects of different preprocessing methods and screening feature methods and combines different modeling methods to conduct experiments. The research results show that the method proposed in this paper has certain effects.

With the development of human society, the shortcomings of the existing transportation system become increasingly prominent, so people hope to use advanced technology to achieve intelligent transportation. However, the recognition rate of most methods of detecting video vehicles is too low and the process is complicated. This paper uses machine learning theory to design a variety of pattern classifiers, including Adaboost, SVM, RF, and SVR algorithms, to classify vehicles. Support vector regression (SVR) is a support vector regression algorithm based on the basic principles of support vector machine (SVM) and then generalized to the regression problem. This paper proposes a short-term traffic flow prediction model based on SVR and optimizes SVM parameters to form an improved SVR short-term traffic flow prediction model. It can be obtained from experiments that the classification error rate of support vector regression (SVR) is the lowest (3.22%). According to the prediction of morning and night peak hours, this paper concludes that the MAPE of SVR is reduced by 19.94% and 42.86%, respectively, and the RMSE is reduced by 29.71% and 47.22%, respectively. Experiments show that the improved algorithm can obtain the optimal parameter combination of SVR faster and better and can effectively improve the accuracy of traffic flow prediction. The target tracking pedestrian counting method proposed in this paper has significantly improved the counting accuracy. The calculation of HOG features can be further expanded, such as the selection of neighborhoods when calculating HOG features, and finally a more efficient pedestrian counting framework is implemented.

Search and rescue are essential applications of disaster management in which people are evacuated from the disaster-prone area to a safer place. This overall process of search and rescue can be more efficient if an automated system can quickly locate the human or area where rescue is required. To provide a faster and accurate search of those places, this paper proposes a novel approach to search and rescue using automated drone surveillance. In this paper, a complex scene classification problem is solved using the proposed 3DCNN model. The proposed model uses spatial as well as temporal features of the video for the classification of the scene as help or non-help in the natural disaster. Due to the unavailability of such kind of dataset, it is impossible to train the model. Therefore, it is essential to develop a dataset for search and rescue. The proposed dataset is a first and unique dataset for scene classification using drone surveillance. The major contribution of this paper is (1) a novel 3DCNN powered model for scene classification in drone surveillance, (2) to develop the required dataset for the training of scene classification model, and (3) particular swarm optimization (PSO)-based hyper-parameter tuning for getting the best value of multiple parameters used for training the model. Our hybridization of parameter tuning with PSO helps for the convergence of parameter values of proposed 3DCNN model, and the proposed scene classification model (3DCNN+PSO) is applied to the dataset. The proposed model gives an impressive performance to help situation identification with 98% training and 99% validation accuracy.

A software defect report is a bug in the software system that developers and users submit to the software defect library during software development and maintenance. Managing a software defect report that is overwhelming is a challenging task. The traditional method is manual identification, which is time-consuming and laborious and delays the repair of important software defects. Based on the above background, the purpose of this paper is to study the software defect prediction (SDP) model based on LASSO–SVM. In this paper, the problem of poor prediction accuracy of most SDP models is proposed. A SDP model combining minimum absolute value compression and selection method and support vector machine algorithm is proposed. Firstly, the feature selection ability of the minimum absolute value compression and selection method is used to reduce the dimension of the original data set, and the data set not related to SDP is removed. Then, the optimal value of SVM is obtained by using the parameter optimization ability of cross-validation algorithm. Finally, the SDP is completed by the nonlinear computing ability of SVM. The accuracy of simulation results is 93.25% and 66.67%, recall rate is 78.04%, and f-metric is 72.72%. The results show that the proposed defect prediction model has higher prediction accuracy than the traditional defect prediction model, and the prediction speed is faster.

Crime forecasting has been one of the most complex challenges in law enforcement today, especially when an analysis tends to evaluate inferable and expanded crime rates, although a few methodologies for subsequent equivalents have been embraced before. In this work, we use a strategy for a time series model and machine testing systems for crime estimation. The paper centers on determining the quantity of crimes. Considering various experimental analyses, this investigation additionally features results obtained from a neural system that could be a significant alternative to machine learning and ordinary stochastic techniques. In this paper, we applied various techniques to forecast the number of possible crimes in the next 5 years. First, we used the existing machine learning techniques to predict the number of crimes. Second, we proposed two approaches, a modified autoregressive integrated moving average model and a modified artificial neural network model. The prime objective of this work is to compare the applicability of a univariate time series model against that of a variate time series model for crime forecasting. More than two million datasets are trained and tested. After rigorous experimental results and analysis are generated, the paper concludes that using a variate time series model yields better forecasting results than the predicted values from existing techniques. These results show that the proposed method outperforms existing methods.