Search

Gastrointestinal (GI) cancer is the most common cancer in men and women. GI cancers are increasing every year worldwide. In the biomedical industry, Radiation treatment is a frequent choice for treating cancers of the GI tract in which the oncologist focuses the high range of X-ray beams on the tumor while avoiding the healthy organs. Manual segmentation of healthy organs to focus X-ray beams only on the tumor portion is very tedious and time-consuming, which can lead the treatment from a few minutes to hours. Deep learning techniques can concur with this problem by segmentation of healthy organs. This research article proposes a deep learning-based model Pyramid Scene Parsing Network (PSPNet) for segmenting organs such as the stomach, small bowel, and large bowel in the GI tract. The model has been simulated with five feature encoding networks: ResNext 50, Timm_Gernet_S, ResNet 34, EfficientNet B1, and MobileNet V2. These encoders were used for downsampling the feature map in the PSPNet architecture. The implementations have been performed using the UW Madison GI tract dataset, which contains 38,496 MRI scans of cancer patients. The model was evaluated using validation dice, Jaccard, and validation loss. The results reveal that the PSPNet model combined with ResNet 34 as encoder outperforms the other feature encoding networks with validation dice as 0.8842, validation Jaccard as 0.8531, and validation loss as 0.1365. Radiation oncologists can use the proposed model to speed up radiation therapy for cancer treatment.

Intelligent Transportation System (ITS) provides services for proper traffic assistance. ITS helps in creating a transportation system that is smart, safe and efficient. Vehicular Ad-hoc Network supplies internet connectivity to vehicles and helps in traffic guidance. This paper uses a modified transformer architecture for time-series vehicular data to predict traffic flow. Time-series sequences are generated from the dataset for capturing temporal dependencies. Our proposed transformer-based model has been engineered to capture inter-feature correlations along with inter-sample correlations. The 2D-Transformers model has a significant decrease in error compared with Transformers and LSTM-based models. The prediction generated from the model can be transmitted throughout a network of vehicles. So, a holistic networking model is proposed where the vehicles will be connected to Road-side Units (RSUs) and the backbone network will be Software Defined Network (SDN). The traditional design principles, that incorporate data, control and management planes together in a network device, are incapable to adapt with this much data growth, bandwidth, speed, security, and scalability compared to SDN as it provides with centralized programmable mechanism reliably. The trained parameters learned using the transformer model can be passed throughout the network for traffic guidance.

Automatic systems to monitor people and subsequently improve people’s lives have been emerging in the last few years, and currently, they are capable of identifying many activities of daily living (ADLs). An important field of research in this context is the monitoring of health risks and the identification of falls. It is estimated that every year, one in three persons older than 65 years will fall, and fall events are associated with high mortality rates among the elderly. We propose an anomaly identification framework to detect falls, which incorporates a spatial-temporal convolutional graph network (ST-GCN) as a feature extractor and uses an encoder process to reconstruct ADLs and identify falls as anomalies. As the publicly available fall datasets are few and generally unbalanced, training a reliable model using approaches that need explicit labeling is challenging. Thus, a focus on learning without external supervision is desirable. Treating a fall as an exception of ADLs allows us to recognize falls as anomalies without explicit labels. Given its modular architecture, our framework can robustly represent visual information and use the encoder’s reconstruction error to identify falls as anomalies. We assess our framework’s ability to recognize falls by training it with only ADLs. We perform three types of experiments: single dataset training and evaluation that consists of separate 90% of the data to train the model 5% to adjust the model, and the rest to the test. A joint dataset experiment, where we combine two datasets to increase the number of samples our model is trained on, and a cross-dataset evaluation, where we train on one dataset and evaluate using another one. Besides presenting state-of-the-art results on our experiments, particularly on the cross-dataset one, the model also presents a low number of false events, which makes it an ideal candidate for real-world application.

Financial and economic news is continuously monitored by financial market participants. According to the efficient market hypothesis, all past information is reflected in stock prices and new information is instantaneously absorbed in determining future stock prices. Hence, prompt extraction of positive or negative sentiments from news is very important for investment decision-making by traders, portfolio managers and investors. Sentiment analysis models can provide an efficient method for extracting actionable signals from the news. However, financial sentiment analysis is challenging due to domain-specific language and unavailability of large labeled datasets. General sentiment analysis models are ineffective when applied to specific domains such as finance. To overcome these challenges, we design an evaluation platform which we use to assess the effectiveness and performance of various sentiment analysis approaches, based on combinations of text representation methods and machine-learning classifiers. We perform more than one hundred experiments using publicly available datasets, labeled by financial experts. We start the evaluation with specific lexicons for sentiment analysis in finance and gradually build the study to include word and sentence encoders, up to the latest available NLP transformers. The results show improved efficiency of contextual embeddings in sentiment analysis compared to lexicons and fixed word and sentence encoders, even when large datasets are not available. Furthermore, distilled versions of NLP transformers produce comparable results to their larger teacher models, which makes them suitable for use in production environments.

Traditional visual simultaneous localization and mapping (SLAM) systems mostly based on small-area static environments. In recent years, some studies focused on combining semantic information with visual SLAM. However, most of them are hard to obtain better performance in the large-scale dynamic environment. And the accuracy, rapidity of the system still needs to strengthen. In this paper, we develop a more efficient semantic SLAM system in the two-wheeled mobile robot by using semantic segmentation to recognize people, chairs, and other objects in every keyframe. With a preliminary understanding of the environment, fusing the RGB-D camera and encoders information, to localization and creating a dense colored octree map without dynamic objects. Besides, for the incomplete identification of movable objects, we used image processing algorithms to enhance the semantic segmentation effect. In the proposed method, enhanced semantic segmentation in keyframes dramatically increases the efficiency of the system. Moreover, fusing the different sensors can highly raise localization accuracy. We conducted experiments on various datasets and in some real environments and compared them with DRE-SLAM, DS-SLAM, to evaluate the performance of the proposed approach. The results suggest we significantly improve the processing efficiency, robustness, and quality of the map.