Video-based fall detection plays a crucial role in telemonitoring as a key component in ensuring timely intervention and safety for older adults who live alone. Despite promising advances, most vision-based fall detection methods remain insufficiently robust and fail to generalize effectively to real-world scenarios. In this paper, we present a comprehensive experimental framework designed to rigorously and generically assess the robustness of fall detection approaches. This framework encompasses three evaluation settings: intra-subject, intersubject, and cross-dataset evaluation. It is validated using a custom architecture that combines a convolutional neural network (CNN) with a bidirectional LSTM (BiLSTM), evaluated on three public datasets: URF, Le2i-FD, and MCFD. Experimental results demonstrate strong generalization, with recall exceeding $80 \%$ in cross-dataset settings. These findings underscore the importance of diverse evaluation strategies in developing reliable fall detection systems.

This paper presents the African Dialect Dataset for Sentiment Analysis, a new natural language processing dataset (AfriDial). This dataset is intended to aid in the classification of multilingual human text using the mother tongue. Around 14k documents in seven distinct dialects, including Tunisian, Moroccan, Chadian, Mauritanian, Burkina Faso, Cameroonian, and Congolese, are included in the AfriDial dataset. The documents, which cover a wide range of subjects like politics, sports, entertainment, and technology, were gathered from open social media and crowdsourcing. Positive, negative, and neutral sentiments are the three classes assigned to each document in the dataset. The AfriDial dataset will be an important tool for researchers working on multilingual text classification and natural language processing (NLP). The paper also presents a baseline model using the transfer learning of bidirectional encoder representations from transformers (BERT) architecture on the AfriDial dataset. An experimental study is presented to introduce more methods and contributions to the field of dialectal NLP

Electrocardiogram (ECG) signal analysis is a crucial tool for enhancing the efficacy of clinical diagnosis, particularly in detecting arrhythmias. However, its performance tends to degrade under the inter-patient paradigm, especially for minority sample categories. To address this issue and enhance the detection performance of these less represented classes within the inter-patient test protocol, this paper proposes a novel hybrid framework. This framework integrates specialized blocks from convolutional networks, namely DeepArr CNN, with sequence-to-sequence BiLSTM models. The proposed approach involves extracting local ECG features from a sequence of heartbeats utilizing DeepArr CNN. These extracted feature maps are then fed into the RNN encoder-decoder to facilitate fusion with the feature maps of neighboring heartbeats. Our proposed method, which adhered to the AMII standard of the MIT-BIH arrhythmia database and operated within the inter-patient paradigm, achieved impressive accuracy rates. Specifically, it yielded accuracy rates of 99.92% and 99.81% for three and five class scenarios, respectively. The performance measures across different classes are as follows: for the N class, sensitivity (SEN) is 99.81%, positive predictive value (PPV) is 99.73%, and specificity (SPEC) is 97.81%; for the S class, SEN is 92.97%, PPV is 96.01%, and SPEC is 99.85%; for the V class, SEN is 99.97%, PPV is 99.26%, and SPEC is 99.95%; and for the F class, SEN is 97.42%, PPV is 95.70%, and SPEC is 99.97%. Even when dealing with an unbalanced dataset, our proposed solution consistently yields remarkable outcomes. Specifically, it achieves an accuracy rate of 99.24% in the three-class scenario and 98.75% in the five-class scenario. These experimental results underscore the effectiveness of our S2SDeepArr model for ECG Classification under the inter-patient paradigm, as demonstrated across various experimental cases.

Cancer is a critical global public health problem with meager median survival. It is therefore quite essential to detect this disease at an early stage to improve diagnostic results and consequently avoid serious complications. For this purpose, various researchers have implemented automated methods with the use of different medical imaging modalities. Accordingly, the expansion of deep learning techniques grants opportunities to enhance diagnosis, cure, and prevention. In this study, a diagnostic system for accurate classification of ultrasound breast abnormalities based on the powerful ResNet-50 CNN is proposed with the aim of providing early detection of breast cancer decease. The contribution of this work lies in the novel approach taken to improve the performance of the ResNet50 model in the classification of ultrasound breast cancer images. Transfer learning allows for the model to leverage pre-existing knowledge, while the application of data augmentation techniques enhances the diversity and quality of the training data. Additionally, the optimization of the batch size as a hyperparameter ensures that the model is able to effectively learn from the training data, leading to improved accuracy and efficiency in the classification process. This approach is crucial in the early detection and treatment of breast cancer. Quantitative and qualitative evaluations have been detailed in this study using Breast Ultrasound Dataset BUSI. Our presented work shows interesting results in terms of accuracy, specificity, sensitivity, and AUC which exceed the performance of other compared works. Moreover, the proposed method helps boost the clinical diagnosis of breast cancer. It may integrate a radiologist network, allowing them to constantly follow up on the patient's medical history.

Despite a great deal of progress in face recognition technologies, current solutions are still vulnerable to spoof attacks. In fact, it is easy to access digital replicas of facial biometric information from readily available photos, videos and 3D masks. The literature contains several face anti spoofing methods that try to detect whether the face in the front of the recognition system is real or an artificial replica. However, these methods are not robust and require many improvements since they are sensitive to lightening conditions and pose variations. In order to address these issues, we propose a novel face anti spoofing method based on Multi Color Convolutional Neural Network (CNN) architecture named DeepColorFASD. Our approach investigates the effect of space colors (RGB, HSV and Y CbCr) on CNN architectures and proposes a fusion based voting method for face anti spoofing. In addition, we also explain the resulting feature maps visualizations. We evaluate our system through an experimental study using CASIA FASD: a well-known face anti spoofing database. The results using this challenging database demonstrate that our solution performs better than recent works as measured by Half Total Error Rate (HTER) and ROC curve.

Lying is among the most common wrong human acts that merits spending time thinking about it. The lie detection is until now posing a problem in recent research which aims to develop a non-contact application in order to estimate physiological changes. In this paper, we have proposed a preliminary investigation on which relevant acoustic parameter can be useful to classify lie or truth from speech signal. Our proposed system in is based on the Mel Frequency Cepstral Coefficient (MFCC) commonly used in automatic speech processing on our own constructed database ReLiDDB (ReGIM-Lab Lie Detection DataBase) for both cases lie detection and person voice recognition. We have performed on this database the Support Vector Machines (SVM) classifier using Linear kernel and we have obtained an accuracy of Lie and Truth detection of speech audio respectively 88.23% and 84.52%.

Security and surveillance are vital issues in today’s world. The recent acts of terrorism have highlighted the urgent need for efficient surveillance. There is indeed a need for an automated system for video surveillance which can detect identity and activity of person. In this article, we propose a new paradigm to recognize an aggressive human behavior such as boxing action. Our proposed system for human activity detection includes the use of a fusion between Spatio Temporal Interest Point (STIP) and Histogram of Oriented Gradient (HoG) features. The novel feature called Spatio Temporal Histogram Oriented Gradient (STHOG). To evaluate the robustness of our proposed paradigm with a local application of HoG technique on STIP points, we made experiments on KTH human action dataset based on Multi Class Support Vector Machines classification. The proposed scheme outperforms basic descriptors like HoG and STIP to achieve 82.26% us an accuracy value of classification rate.

To control the state of horses in the born, breeders needs a monitoring system with a surveillance camera that can identify and distinguish between horses. We proposed in [5] a method of horse’s identification at a distance using the frontal facial biometric modality. Due to the change of views, the face recognition becomes more difficult. In this paper, the number of images used in our THoDBRL’2015 database (Tunisian Horses DataBase of Regim Lab) is augmented by adding other images of other views. Thus, we used front, right and left profile face’s view. Moreover, we suggested an approach for multiview face recognition. First, we proposed to use the Gabor filter for face characterization. Next, due to the augmentation of the number of images, and the large number of Gabor features, we proposed to test the Deep Neural Network with the auto-encoder to obtain the more pertinent features and to reduce the size of features vector. Finally, we performed the proposed approach on our THoDBRL’2015 database and we used the linear SVM for classification.

The online writer identification is a required component in many applications of Computer vision and Pattern Recognition. The offline writer identification is more developed in literature due to the use of traditional system based on Image Processing. There is a lack of works done in the case of online writer identification. In this paper, we propose a novel method to text independent writer identification from online handwriting. Our proposed method is based on the use of Beta-elliptic model that computes efficiently on real time writing movements in online handwriting by involving simultaneously its both profile entities: the Beta impulses and the elliptic arcs. The information provided by the feature extraction is used in a Deep Neural Network as classifier. The obtained results show that the proposed online writer identification method is worth to receive further exploration in capturing the writer's individual. The use of the Deep Neural Network provides more robustness to identification of writers.

This paper proposes an automatic text-independent online Arabic writer identification system. The main contribution of our system is to explore the utility of Beta-elliptic model in features extraction for online writer identification, due to the rich output of Beta-elliptic model in terms of graphical, kinematical and biometrical data. The efficiency of the considered features has been evaluated using feed forward neural network classifier. Experimental results on ADAB Database show the performance of the proposed system in online Arabic writer identification task.

This paper presents a comprehensive experimental study on face recognition to prove that holistic approaches are more robust than geometric and local approaches in order to address the problem of which method holistic or geometric can assist to face recognition. This work is done based on the motivation to integrate soft biometric traits into face recognition systems using same computing. A bag of features extraction and classification combined with each other to find the most appropriate technique that can enhance face recognition task. The experimental study shows that the texture information is discriminant in facial images representation, Gabor filter is more useful than Local Binary Pattern, a space dimensionality reduction using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) is very interesting to increase recognition rates. The fusion between Gabor, PCA or LDA and Multi class Support Vector Machines (SVM) ranks top the list of all other combinations.These techniques will be performed later to integrate soft biometrics.

Horses recognition is an important task especially for horses' trainers. It is necessary in this case to identify each horse to be distinguished. All methods used for identification are invasive and threaten the well-being of horses like Tatto and Freeze branding. So, for this reason we aim to create a human method of identification using the facial biometric modality. We tested the Gabor and LBP features for face characterization and the Euclidian and Mahcosine distance for classification. We performed our approaches on our database "THoFDRL'2015 database: Horses Face Database of REGIM Lab" and we used only horses' faces in front view. These faces are considered for experimentation. The recognition rate is 95.74%. This result maintains the success of our approach in horse recognition.

Face recognition is a very popular biometric solution in the literature. Several solutions are presented to meet the needs of individual's verification or identification. There are three types of face recognition approaches: local, global and hybrid. In this paper, we proposed a local approach for face recognition based on combined features selection methods like Genetic algorithm, Gramdt Shmidt algorithm, mRmR features selection algorithm and naïve Bayesian classifier. Our proposed approach will be compared with some face recognition systems based on global features. A comparative study is given in this paper based on Recognition rates and Execution times. Our Face recognition system, which is based on naïve Bayesian classifier and tested on ORL face database, has showed 78.75% recognition rate and interesting execution times compared to global approaches.