💻 computer science

An integrated sociotechnical reference model for aligning artificial intelligence implementation in organizations

Using a Design Science Research approach, this study addresses the misalignment between AI implementation and organizational transformation by analyzing existing procedural models to construct the Integrated Sociotechnical AI Reference Model (ISAR-M), which synchronizes technical capabilities with organizational readiness to overcome disciplinary silos and ensure successful AI adoption.

Alexander Katzorke, Florian Dober, Sebastian Floerecke, Alexander Herzfeldt, Christoph Ertl2026-08-18
💻 computer science

Self-Supervised Multi-Modal Transformer for Early Brain Tumor Prediction Using Super-Resolution MRI and ICU Time-Series Data

This paper introduces the Self-Supervised Multi-Modal Transformer (SS-MMT), a novel deep learning framework that combines GAN-enhanced super-resolution MRI with ICU time-series data via masked autoencoder pre-training and cross-modal attention to achieve state-of-the-art early brain tumor prediction with an AUC-ROC of 0.945.

Angothu Govind, Prof.T Kishore Kumare2026-08-15
💻 computer science

Subject-Calibrated Attention-State Classification during Digital Cognitive Tasks via MTFF: Band-Token Cross-Band Fusion on Single-Channel EEG

This paper proposes MTFF, a lightweight Transformer-based framework that fuses intra-band rhythmic patterns from five canonical EEG frequency bands into learnable tokens to achieve robust attention-state classification from noisy, single-channel EEG signals in digital cognitive tasks.

Jin Feng, Jing He, Yong Fan, Junwei Huang, Chenliang Jiang, Yunde Li, Guowei Liu, ZhaoLe Yu2026-08-15
💻 computer science

Bridging communication between hearing and visually impaired individuals via speech recognition and synthesis

This paper presents a cost-effective, software-only Speech Recognition and Synthesis Tool (SRST) developed in MATLAB that facilitates bidirectional communication between hearing and visually impaired individuals by converting speech to high-contrast text and text to synthesized speech, achieving approximately 90% operational efficiency without requiring specialized hardware.

Dawit Teklu Weldeslasie, Mehamed Ahmed Abdurrahman, Yonas Desta Sheshegu2026-08-14
💻 computer science

Exact Transfer-Matrix Evaluation Reveals Operating-Point Limits and Opportunities for Fidelity Quantum Kernels in Biomedical Abstract Screening

This study demonstrates that while an exact transfer-matrix method enables efficient evaluation of fidelity quantum kernels for biomedical abstract screening, the resulting models fail to surpass strong classical baselines in overall ranking performance despite offering specific improvements in operating-point utility at high sensitivity thresholds.

Tyler Pitre2026-08-14
💻 computer science

How Fast, How Sure, and Where It Breaks: A Streaming Sequential-Decision Layer for Voice-Deepfake Detection under Real Telephony Codecs

This paper introduces a streaming sequential-decision layer for voice-deepfake detection that, while unable to improve raw accuracy under real telephony codecs, significantly reduces committed-call error by leveraging early confidence-based abstention and highlights that calibration must be adapted to specific channel conditions to avoid severe overconfidence.

Ilja Semjonovs2026-08-14
💻 computer science

Restoring the Neural-Symbolic Bridge via Execution-Grounded Reward Shaping in Large Language Models

This paper proposes ReinKBQA, a reinforcement learning framework that restores the neural-symbolic bridge in Large Language Models for Knowledge Base Question Answering by leveraging execution-grounded, multi-dimensional rewards (via GRPO) to overcome the limitations of supervised fine-tuning on formal languages with sparse pre-training priors, achieving state-of-the-art performance on complex reasoning benchmarks.

Zhengyu Lyu, Aziguli Wulamu2026-08-14
💻 computer science

A Component-Based Multi-Tier Web Architecture for Enhancing ERP System Development Efficiency and Maintainability

This paper proposes and validates a component-based multi-tier web architecture that integrates object-oriented design and event-driven programming to significantly enhance ERP system development efficiency, maintainability, and scalability, demonstrating a 44% reduction in development effort through a practical case study.

Yonghua Li, Yan Zhang, AOli Jiao, Hongle Du, changqiang jing2026-08-14