List of Content
Back to Listing
| Title | Abstract | Action(s) |
|---|---|---|
| PREDICTING COURIER NODE TRAJECTORY USING CHANNEL CHARACTERIZATION TO IMPROVE NETWORK LIFETIME IN UWSNS | Underwater Wireless Sensor Networks (UWSNs) are essential for numerous applications, such as oceanic monitoring and military surveillance which require effective communications. The communication range and network lifetime are the major challenges for UWSNs, particularly due to limitations of acoustic wave-based communication. These limitations include low data rates and high latency and also include vulnerability to temperature and salinity. This research investigates the usability of Electromagnetic (EM) waves in short-range communications, detailing their benefits from higher data rates to lower delays but with limited range compared to acoustics. In response to these challenges, this research develops a comprehensive approach that merges environmental data from the National Centers for Environmental Information dataset, including temperature, salinity, and depth variations recorded between 1955 and 2012. Among others, Helmholtz, Stogryn, and Ellison Models are implemented and used to study the behavior of EM wave propagation in an underwater channel. It also involves the development of a trajectory prediction approach for AUVs or courier nodes towards optimizing the communication range with the least energy consumption. Using the proposed courier node trajectory prediction technique, the network achieved a 98% improvement in Network Lifetime and an 82% increase in successful Packet Delivery. Overall, the approach led to a 50% enhancement in network efficiency, ensuring longer and sustained energy usage throughout the simulation. This research thus proved that EM waves can be used in achieving efficient underwater communication based on accurate trajectory prediction and realistic channel characterization. |
|
| A DEEP LEARNING METHOD FOR INNER SPEECH CLASSIFICATION USING EEG SIGNAL | This thesis studies utilizing electroencephalography (EEG) signals the difficulties of subject-independent inner speech classification. Particularly for those with severe motor disabilities, inner speech the act of silently communicating to oneself offers a potential modality for Brain-Computer Interfaces (BCIs). Low signal-to-noise ratios and great inter-subject variability make deciphering inner speech from EEG difficult, nevertheless. Based on EEG data, this thesis evaluates several machine learning and deep learning models for inner speech classification. Particularly, a deep learning model, a Convolutional Neural Network (CNN) with triplet loss, is contrasted against conventional machine learning methods including Linear Support Vector Machine (SVM), More general SVM with various kernels, and LightGBM. Subject-independent framework with leave-one-subject-out cross-valuation on the Thinking Out Loud (TOL) dataset evaluates the models. Performance is evaluated with reference to accuracy, F1-score, precision, and recall. The CNN-based triplet network achieves the best average accuracy among other models, so the results show the promise of deep learning for subject-independent inner speech classification. Although the results imply that deep learning presents a viable path for future research, especially with bigger and more diverse datasets and advanced architectures, benefits over conventional approaches are minor. This work advances knowledge of the difficulties and possible solutions for creating strong, generally applicable inner voice BCIs. |
|