ROC curve for binary classification. by Nicodemus Songose Awarayi (18414494)

“…The model further showed superior results on binary classification compared with existing methods. …”

Confusion matrix for binary classification. by Nicodemus Songose Awarayi (18414494)

“…The model further showed superior results on binary classification compared with existing methods. …”

Summary of existing CNN models. by Nicodemus Songose Awarayi (18414494)

“…The model further showed superior results on binary classification compared with existing methods. …”

Using Variable Data-Independent Acquisition for Capillary Electrophoresis-Based Untargeted Metabolomics by Saki Kiuchi (19374255)

“…Capillary electrophoresis coupled with tandem mass spectrometry (CE-MS/MS) offers advantages in peak capacity and sensitivity for metabolic profiling owing to the electroosmotic flow-based separation. However, the utilization of data-independent MS/MS acquisition (DIA) is restricted due to the absence of an optimal procedure for analytical chemistry and its related informatics framework. …”

Using Variable Data-Independent Acquisition for Capillary Electrophoresis-Based Untargeted Metabolomics by Saki Kiuchi (19374255)

“…Capillary electrophoresis coupled with tandem mass spectrometry (CE-MS/MS) offers advantages in peak capacity and sensitivity for metabolic profiling owing to the electroosmotic flow-based separation. However, the utilization of data-independent MS/MS acquisition (DIA) is restricted due to the absence of an optimal procedure for analytical chemistry and its related informatics framework. …”

Testing results for classifying AD, MCI and NC. by Nicodemus Songose Awarayi (18414494)

“…The model further showed superior results on binary classification compared with existing methods. …”

Algoritmo de clasificación de expresiones de odio por tipos en español (Algorithm for classifying hate expressions by type in Spanish) by Daniel Pérez Palau (11097348)

“…</li></ul><p dir="ltr"><b>File Structure</b></p><p dir="ltr">The code generates and saves:</p><ul><li>Weights of the trained model (.h5)</li><li>Configured tokenizer</li><li>Training history in CSV</li><li>Requirements file</li></ul><p dir="ltr"><b>Important Notes</b></p><ul><li>The model excludes category 2 during training</li><li>Implements transfer learning from a pre-trained model for binary hate detection</li><li>Includes early stopping callbacks to prevent overfitting</li><li>Uses class weighting to handle category imbalances</li></ul><p dir="ltr">The process of creating this algorithm is explained in the technical report located at: Blanco-Valencia, X., De Gregorio-Vicente, O., Ruiz Iniesta, A., & Said-Hung, E. (2025). …”

Table_1_Computational prediction of promotors in Agrobacterium tumefaciens strain C58 by using the machine learning technique.DOCX by Hasan Zulfiqar (12117255)

“…In the model, promotor sequences were encoded by three different kinds of feature descriptors, namely, accumulated nucleotide frequency, k-mer nucleotide composition, and binary encodings. …”

Priority rule-based heuristics for distributed multi-project scheduling considering global resource failures by Xuejun Hu (2003440)

Processed dataset to train and test the WGAN-GP_IMOA_DA_Ensemble model by Ramya Chinnasamy (21633527)

“…To overcome these limitations, we propose a hybrid framework named WGAN-GP_IMOA_DA_Ensemble. This framework integrates a novel biologically inspired optimization algorithm, the Indian Millipede Optimization Algorithm (IMOA), for effective feature selection. …”

An Ecological Benchmark of Photo Editing Software: A Comparative Analysis of Local vs. Cloud Workflows by Pierre-Alexis DELAROCHE (22092572)

“…Experimental Methodology Framework Local Processing Pipeline Architecture Data Flow: Storage I/O → Memory Buffer → CPU/GPU Processing → Cache Coherency → Storage I/O ├── Input Vector: mmap() system call for zero-copy file access ├── Processing Engine: OpenMP parallelization with NUMA-aware thread affinity ├── Memory Management: Custom allocator with hugepage backing └── Output Vector: Direct I/O bypassing kernel page cache Cloud Processing Pipeline Architecture Data Flow: Local Storage → Network Stack → TLS Tunnel → CDN Edge → Origin Server → Processing Grid → Response Pipeline ├── Upload Phase: TCP window scaling with congestion control algorithms ├── Network Layer: Application-layer protocol with adaptive bitrate streaming ├── Server-side Processing: Containerized microservices on Kubernetes orchestration ├── Load Balancing: Consistent hashing with geographic affinity routing └── Download Phase: HTTP/2 multiplexing with server push optimization Dataset Schema and Semantic Structure Primary Data Vectors Field Data Type Semantic Meaning Measurement Unit test_type Categorical Processing paradigm identifier {local_processing, cloud_processing} photo_count Integer Cardinality of input asset vector Count avg_file_size_mb Float64 Mean per-asset storage footprint Mebibytes (2^20 bytes) total_volume_gb Float64 Aggregate data corpus size Gigabytes (10^9 bytes) processing_time_sec Integer Wall-clock execution duration Seconds (SI base unit) cpu_usage_watts Float64 Thermal design power consumption Watts (Joules/second) ram_usage_mb Integer Peak resident set size Mebibytes network_upload_mb Float64 Egress bandwidth utilization Mebibytes energy_consumption_kwh Float64 Cumulative energy expenditure Kilowatt-hours co2_equivalent_g Float64 Carbon footprint estimation Grams CO₂e test_date ISO8601 Temporal execution marker RFC 3339 format hardware_config String Node topology identifier Alphanumeric encoding Statistical Distribution Characteristics The dataset exhibits non-parametric distribution patterns with significant heteroscedasticity across computational load vectors. …”

Data_Sheet_1_The impact of family urban integration on migrant worker mental health in China.docx by Xiaotong Sun (6535064)

“…We applied binary logit regression models to analyze the influence of family urban integration on the mental health among migrant workers. …”

<b>AI for imaging plant stress in invasive species </b>(dataset from the article https://doi.org/10.1093/aob/mcaf043) by Erola Fenollosa (20977421)

“…The described extracted features were used to predict leaf betalain content (µg per FW) using multiple machine learning regression algorithms (Linear regression, Ridge regression, Gradient boosting, Decision tree, Random forest and Support vector machine) using the <i>Scikit-learn</i> 1.2.1 library in Python (v.3.10.1) (list of hyperparameters used is given in <a href="#sup1" target="_blank">Supplementary Data S5</a>). …”