Examining Deep Learning Architectures for Crime Classification and Prediction

In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented. We examine the effectiveness of deep learning algorithms in this domain and provide recommendations for designing and training deep learning systems for predicting crime areas, using open data from police reports. Having time-series of crime types per location as training data, a comparative study of 10 state-of-the-art methods against 3 different deep learning configurations is conducted. In our experiments with 5 publicly available datasets, we demonstrate that the deep learning-based methods consistently outperform the existing best-performing methods. Moreover, we evaluate the effectiveness of different parameters in the deep learning architectures and give insights for configuring them to achieve improved performance in crime classification and finally crime prediction.

Download Full-text

Sequence-to-function deep learning frameworks for engineered riboregulators

Nature Communications ◽

10.1038/s41467-020-18676-2 ◽

2020 ◽

Vol 11 (1) ◽

Cited By ~ 2

Author(s):

Jacqueline A. Valeri ◽

Katherine M. Collins ◽

Pradeep Ramesh ◽

Miguel A. Alcantar ◽

Bianca A. Lepe ◽

...

Keyword(s):

Computer Vision ◽

Deep Learning ◽

Nucleic Acid ◽

Language Processing ◽

Training Data ◽

Design Rules ◽

Improved Performance ◽

Circuit Components ◽

Learning Frameworks ◽

Learning Architectures

Abstract While synthetic biology has revolutionized our approaches to medicine, agriculture, and energy, the design of completely novel biological circuit components beyond naturally-derived templates remains challenging due to poorly understood design rules. Toehold switches, which are programmable nucleic acid sensors, face an analogous design bottleneck; our limited understanding of how sequence impacts functionality often necessitates expensive, time-consuming screens to identify effective switches. Here, we introduce Sequence-based Toehold Optimization and Redesign Model (STORM) and Nucleic-Acid Speech (NuSpeak), two orthogonal and synergistic deep learning architectures to characterize and optimize toeholds. Applying techniques from computer vision and natural language processing, we ‘un-box’ our models using convolutional filters, attention maps, and in silico mutagenesis. Through transfer-learning, we redesign sub-optimal toehold sensors, even with sparse training data, experimentally validating their improved performance. This work provides sequence-to-function deep learning frameworks for toehold selection and design, augmenting our ability to construct potent biological circuit components and precision diagnostics.

Download Full-text

Copy-Move Forgery Detection (CMFD) Using Deep Learning for Image and Video Forensics

Journal of Imaging ◽

10.3390/jimaging7030059 ◽

2021 ◽

Vol 7 (3) ◽

pp. 59

Author(s):

Yohanna Rodriguez-Ortega ◽

Dora M. Ballesteros ◽

Diego Renza

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Training Data ◽

Video Editing ◽

Forgery Detection ◽

Copy Move Forgery Detection ◽

The Impact ◽

And Training ◽

Selection Of ◽

Traditional Image

With the exponential growth of high-quality fake images in social networks and media, it is necessary to develop recognition algorithms for this type of content. One of the most common types of image and video editing consists of duplicating areas of the image, known as the copy-move technique. Traditional image processing approaches manually look for patterns related to the duplicated content, limiting their use in mass data classification. In contrast, approaches based on deep learning have shown better performance and promising results, but they present generalization problems with a high dependence on training data and the need for appropriate selection of hyperparameters. To overcome this, we propose two approaches that use deep learning, a model by a custom architecture and a model by transfer learning. In each case, the impact of the depth of the network is analyzed in terms of precision (P), recall (R) and F1 score. Additionally, the problem of generalization is addressed with images from eight different open access datasets. Finally, the models are compared in terms of evaluation metrics, and training and inference times. The model by transfer learning of VGG-16 achieves metrics about 10% higher than the model by a custom architecture, however, it requires approximately twice as much inference time as the latter.

Download Full-text

AI-MHC: an allele-integrated deep learning framework for improving Class I & Class II HLA-binding predictions

10.1101/318881 ◽

2018 ◽

Cited By ~ 5

Author(s):

John-William Sidhom ◽

Drew Pardoll ◽

Alexander Baras

Keyword(s):

Neural Network ◽

Deep Learning ◽

Immune System ◽

State Of The Art ◽

Class Ii ◽

Class I ◽

Binding Prediction ◽

Translational Invariance ◽

Mhc Molecules ◽

Improved Performance

AbstractMotivationThe immune system has potential to present a wide variety of peptides to itself as a means of surveillance for pathogenic invaders. This means of surveillances allows the immune system to detect peptides derives from bacterial, viral, and even oncologic sources. However, given the breadth of the epitope repertoire, in order to study immune responses to these epitopes, investigators have relied on in-silico prediction algorithms to help narrow down the list of candidate epitopes, and current methods still have much in the way of improvement.ResultsWe present Allele-Integrated MHC (AI-MHC), a deep learning architecture with improved performance over the current state-of-the-art algorithms in human Class I and Class II MHC binding prediction. Our architecture utilizes a convolutional neural network that improves prediction accuracy by 1) allowing one neural network to be trained on all peptides for all alleles of a given class of MHC molecules by making the allele an input to the net and 2) introducing a global max pooling operation with an optimized kernel size that allows the architecture to achieve translational invariance in MHC-peptide binding analysis, making it suitable for sequence analytics where a frame of interest needs to be learned in a longer, variable length sequence. We assess AI-MHC against internal independent test sets and compare against all algorithms in the IEDB automated server benchmarks, demonstrating our algorithm achieves state-of-the-art for both Class I and Class II prediction.Availability and ImplementationAI-MHC can be used via web interface at baras.pathology.jhu.edu/[email protected]

Download Full-text

Unsupervised Deep Learning via Affinity Diffusion

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6757 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11029-11036

Author(s):

Jiabo Huang ◽

Qi Dong ◽

Shaogang Gong ◽

Xiatian Zhu

Keyword(s):

Deep Learning ◽

State Of The Art ◽

General Purpose ◽

Training Data ◽

Learning Approach ◽

Model Learning ◽

Feature Representations ◽

Discriminative Feature ◽

Training Samples ◽

Unsupervised Deep Learning

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

Download Full-text

Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network

Applied Sciences ◽

10.3390/app10217817 ◽

2020 ◽

Vol 10 (21) ◽

pp. 7817

Author(s):

Ivana Marin ◽

Ana Kuzmanic Skelin ◽

Tamara Grujic

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Empirical Evaluation ◽

Training Data ◽

Generalization Performance ◽

Deep Model ◽

Unseen Data ◽

Regularization Techniques ◽

Learning Architectures

The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion-MNIST image datasets.

Download Full-text

Comparing Deep-Learning Architectures and Traditional Machine-Learning Approaches for Satire Identification in Spanish Tweets

Mathematics ◽

10.3390/math8112075 ◽

2020 ◽

Vol 8 (11) ◽

pp. 2075

Author(s):

Óscar Apolinario-Arzube ◽

José Antonio García-Díaz ◽

José Medina-Moreira ◽

Harry Luna-Aveiga ◽

Rafael Valencia-García

Keyword(s):

Machine Learning ◽

Deep Learning ◽

User Interfaces ◽

State Of The Art ◽

Learning Approaches ◽

Word Embeddings ◽

Linguistic Features ◽

Intended Meaning ◽

Language User ◽

Learning Architectures

Automatic satire identification can help to identify texts in which the intended meaning differs from the literal meaning, improving tasks such as sentiment analysis, fake news detection or natural-language user interfaces. Typically, satire identification is performed by training a supervised classifier for finding linguistic clues that can determine whether a text is satirical or not. For this, the state-of-the-art relies on neural networks fed with word embeddings that are capable of learning interesting characteristics regarding the way humans communicate. However, as far as our knowledge goes, there are no comprehensive studies that evaluate these techniques in Spanish in the satire identification domain. Consequently, in this work we evaluate several deep-learning architectures with Spanish pre-trained word-embeddings and compare the results with strong baselines based on term-counting features. This evaluation is performed with two datasets that contain satirical and non-satirical tweets written in two Spanish variants: European Spanish and Mexican Spanish. Our experimentation revealed that term-counting features achieved similar results to deep-learning approaches based on word-embeddings, both outperforming previous results based on linguistic features. Our results suggest that term-counting features and traditional machine learning models provide competitive results regarding automatic satire identification, slightly outperforming state-of-the-art models.

Download Full-text

Comprehensive evaluation of deep learning architectures for prediction of DNA/RNA sequence binding specificities

Bioinformatics ◽

10.1093/bioinformatics/btz339 ◽

2019 ◽

Vol 35 (14) ◽

pp. i269-i277 ◽

Cited By ~ 24

Author(s):

Ameni Trabelsi ◽

Mohamed Chaabane ◽

Asa Ben-Hur

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Rna Binding ◽

Binding Specificity ◽

Training Data ◽

Supplementary Information ◽

Recurrent Networks ◽

Dna And Rna ◽

Learning Architectures ◽

Dna And Rna Binding

Abstract Motivation Deep learning architectures have recently demonstrated their power in predicting DNA- and RNA-binding specificity. Existing methods fall into three classes: Some are based on convolutional neural networks (CNNs), others use recurrent neural networks (RNNs) and others rely on hybrid architectures combining CNNs and RNNs. However, based on existing studies the relative merit of the various architectures remains unclear. Results In this study we present a systematic exploration of deep learning architectures for predicting DNA- and RNA-binding specificity. For this purpose, we present deepRAM, an end-to-end deep learning tool that provides an implementation of a wide selection of architectures; its fully automatic model selection procedure allows us to perform a fair and unbiased comparison of deep learning architectures. We find that deeper more complex architectures provide a clear advantage with sufficient training data, and that hybrid CNN/RNN architectures outperform other methods in terms of accuracy. Our work provides guidelines that can assist the practitioner in choosing an appropriate network architecture, and provides insight on the difference between the models learned by convolutional and recurrent networks. In particular, we find that although recurrent networks improve model accuracy, this comes at the expense of a loss in the interpretability of the features learned by the model. Availability and implementation The source code for deepRAM is available at https://github.com/MedChaabane/deepRAM. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Brewery: deep learning and deeper profiles for the prediction of 1D protein structure annotations

Bioinformatics ◽

10.1093/bioinformatics/btaa204 ◽

2020 ◽

Vol 36 (12) ◽

pp. 3897-3898

Author(s):

Mirko Torrisi ◽

Gianluca Pollastri

Keyword(s):

Deep Learning ◽

State Of The Art ◽

Solvent Accessibility ◽

Protein Structures ◽

Evolutionary Information ◽

Relative Solvent Accessibility ◽

Multiple Sources ◽

Contact Density ◽

And Training ◽

The Web

Abstract Motivation Protein structural annotations (PSAs) are essential abstractions to deal with the prediction of protein structures. Many increasingly sophisticated PSAs have been devised in the last few decades. However, the need for annotations that are easy to compute, process and predict has not diminished. This is especially true for protein structures that are hardest to predict, such as novel folds. Results We propose Brewery, a suite of ab initio predictors of 1D PSAs. Brewery uses multiple sources of evolutionary information to achieve state-of-the-art predictions of secondary structure, structural motifs, relative solvent accessibility and contact density. Availability and implementation The web server, standalone program, Docker image and training sets of Brewery are available at http://distilldeep.ucd.ie/brewery/. Contact [email protected]

Download Full-text

Detection of Target Persons Using Deep Learning and Training Data Generation for Tsukuba Challenge

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2018.p0513 ◽

2018 ◽

Vol 30 (4) ◽

pp. 513-522 ◽

Cited By ~ 3

Author(s):

Yuichi Konishi ◽

◽

Kosuke Shigematsu ◽

Takashi Tsubouchi ◽

Akihisa Ohya

Keyword(s):

Deep Learning ◽

Autonomous Navigation ◽

Detection System ◽

Computational Cost ◽

Weather Conditions ◽

Recognition System ◽

Training Data ◽

Urban Setting ◽

Data Generation ◽

And Training

The Tsukuba Challenge is an open experiment competition held annually since 2007, and wherein the autonomous navigation robots developed by the participants must navigate through an urban setting in which pedestrians and cyclists are present. One of the required tasks in the Tsukuba Challenge from 2013 to 2017 was to search for persons wearing designated clothes within the search area. This is a very difficult task since it is necessary to seek out these persons in an environment that includes regular pedestrians, and wherein the lighting changes easily because of weather conditions. Moreover, the recognition system must have a light computational cost because of the limited performance of the computer that is mounted onto the robot. In this study, we focused on a deep learning method of detecting the target persons in captured images. The developed detection system was expected to achieve high detection performance, even when small-sized input images were used for deep learning. Experiments demonstrated that the proposed system achieved better performance than an existing object detection network. However, because a vast amount of training data is necessary for deep learning, a method of generating training data to be used in the detection of target persons is also discussed in this paper.

Download Full-text

Deep Learning Control for Digital Feedback Systems: Improved Performance with Robustness against Parameter Change

10.20944/preprints202104.0664.v1 ◽

2021 ◽

Author(s):

Nuha A. S. Alwan ◽

Zahir M. Hussain

Keyword(s):

Deep Learning ◽

Reference Signal ◽

Training Data ◽

Digital Controller ◽

Digital Control System ◽

Parameter Change ◽

Feedback Systems ◽

Unit Step ◽

System Output ◽

Improved Performance

Training data for a deep learning (DL) neural network (NN) controller are obtained from the input and output signals of a conventional digital controller that is designed to provide the suitable control signal to a speciﬁed plant within a feedback digital control system. It is found that if the DL controller is suﬃciently deep (four hidden layers), it can outperform the conventional controller in terms of settling time of the system output transient response to a unit-step reference signal. That is, the DL controller introduces a damping eﬀect. Moreover, it does not need to be retrained to operate with a reference signal of diﬀerent magnitude, or under system parameter change. Such properties make the DL control more attractive for applications that may undergo parameter variation, like sensor networks.

Download Full-text