Explore the vast range of titles available.

Hyperdimensional Computing (HDC) offers a robust and energy-efficient paradigm for edge intelligence; however, current hardware accelerators are often proprietary, tailored to the target learning task and tightly coupled to specific CPU microarchitectures, limiting portability and adoption. To address this, and democratize the deployment of HDC hardware, we present a general-purpose, plug-and-play accelerator IP that implements the Binary Spatter Code framework as a standalone, host-agnostic module. The design is compliant with the AMBA AXI4 standard and provides an AXI4-Lite control plane and DMA-driven AXI4-Stream datapaths coupled to a banked scratchpad memory. The architecture supports synthesis-time scalability, enabling high-throughput transfers independently of the host processor, while employing microarchitectural optimizations to minimize silicon area. A multi-layer C++ software (GitHub repository commit 3ae3b46) stack running in Linux userspace provides a unified programming model, abstracting low-level hardware interactions and enabling the composition of complex HDC pipelines. Implemented on a Xilinx Zynq XC7Z020 SoC, the accelerator achieves substantial gains over an ARM Cortex-A9 baseline, with primitive-level speedups of up to 431×. On end-to-end classification benchmarks, the system delivers average speedups of 68.45× for training and 93.34× for inference. The complete RTL and software stack are released as open-source hardware to support reproducible research and rapid adoption on heterogeneous SoCs.

High-performance embedded systems with powerful processors, specialized hardware accelerators, and advanced software techniques are all key technologies driving the growth of the IoT. By combining hardware and software techniques, it is possible to increase the overall reliability and safety of these systems by designing embedded architectures that can continue to function correctly in the event of a failure or malfunction. In this work, we fully investigate the integration of a configurable hardware vector acceleration unit in the fault-tolerant RISC-V Klessydra-fT03 soft core, introducing two different redundant vector co-processors coupled with the Interleaved-Multi-Threading paradigm on which the microprocessor is based. We then illustrate the pros and cons of both approaches, comparing their impacts on performance and hardware utilization with their vulnerability, presenting a quantitative large-fault-injection simulation analysis on typical vector computing benchmarks, and comparing and classifying the obtained results. The results demonstrate, under specific conditions, that it is possible to add a hardware co-processor to a fault-tolerant microprocessor, improving performance without degrading safety and reliability.

The modular composite representation (MCR) is a computing model that represents information with high-dimensional integer vectors using modular arithmetic. Originally proposed as a generalization of the binary spatter code model, it aims to provide higher representational power while remaining a lighter alternative to models requiring high-precision components. Despite this potential, MCR has received limited attention. Systematic analyses of its trade-offs and comparisons with other models are lacking, sustaining the perception that its added complexity outweighs the improved expressivity. In this work, we revisit MCR by presenting its first extensive evaluation, demonstrating that it achieves a unique balance of capacity, accuracy, and hardware efficiency. Experiments measuring capacity demonstrate that MCR outperforms binary and integer vectors while approaching complex-valued representations at a fraction of their memory footprint. Evaluation on 123 datasets confirms consistent accuracy gains and shows that MCR can match the performance of binary spatter codes using up to 4x less memory. We investigate the hardware realization of MCR by showing that it maps naturally to digital logic and by designing the first dedicated accelerator. Evaluations on basic operations and 7 selected datasets demonstrate a speedup of up to 3 orders of magnitude and significant energy reductions compared to software implementation. When matched for accuracy against binary spatter codes, MCR achieves on average 3.08x faster execution and 2.68x lower energy consumption. These findings demonstrate that, although MCR requires more sophisticated operations than binary spatter codes, its modular arithmetic and higher per-component precision enable lower dimensionality. When realized with dedicated hardware, this results in a faster, more energy-efficient, and high-precision alternative to existing models.

Hyperdimensional Computing (HDC), also known as Vector Symbolic Architectures, is a computing paradigm that combines the strengths of symbolic reasoning with the efficiency and scalability of distributed connectionist models in artificial intelligence. HDC has recently emerged as a promising alternative for performing learning tasks in resource-constrained environments thanks to its energy and computational efficiency, inherent parallelism, and resilience to noise and hardware faults. This work introduces the Hyperdimensional Contextual Bandits (HD-CB): the first exploration of HDC to model and automate sequential decision-making Contextual Bandits (CB) problems. The proposed approach maps environmental states in a high-dimensional space and represents each action with dedicated hypervectors (HVs). At each iteration, these HVs are used to select the optimal action for the given context and are updated based on the received reward, replacing computationally expensive ridge regression procedures required by traditional linear CB algorithms with simple, highly parallel vector operations. We propose four HD-CB variants, demonstrating their flexibility in implementing different exploration strategies, as well as techniques to reduce memory overhead and the number of hyperparameters. Extensive simulations on synthetic datasets and a real-world benchmark reveal that HD-CB consistently achieves competitive or superior performance compared to traditional linear CB algorithms, while offering faster convergence time, lower computational complexity, improved scalability, and high parallelism.

As the Internet of Things expands, embedding Artificial Intelligence algorithms in resource-constrained devices has become increasingly important to enable real-time, autonomous decision-making without relying on centralized cloud servers. However, implementing and executing complex algorithms in embedded devices poses significant challenges due to limited computational power, memory, and energy resources. This paper presents algorithmic and hardware techniques to efficiently implement two LinearUCB Contextual Bandits algorithms on resource-constrained embedded devices. Algorithmic modifications based on the Sherman-Morrison-Woodbury formula streamline model complexity, while vector acceleration is harnessed to speed up matrix operations. We analyze the impact of each optimization individually and then combine them in a two-pronged strategy. The results show notable improvements in execution time and energy consumption, demonstrating the effectiveness of combining algorithmic and hardware optimizations to enhance learning models for edge computing environments with low-power and real-time requirements.

Objective: The aim of this meta-analysis was to discuss evidence supporting the efficacy of adjuvant human papillomavirus (HPV) vaccination in reducing the risk of recurrent cervical intraepithelial neoplasia (CIN) 2 or greater after surgical treatment. Methods: A systematic literature search was performed for studies reporting the impact of HPV vaccination on reducing the risk of recurrence of CIN 2+ after surgical excision. Results were reported as mean differences or pooled odds ratios (OR) with 95% confidence intervals (95% CI). Results: Eleven studies met the inclusion criteria and were selected for analysis. In total, 21,310 patients were included: 4039 (19%) received peri-operational adjuvant HPV vaccination while 17,271 (81%) received surgery alone. The recurrence of CIN 2+ after treatment was significantly lower in the vaccinated compared with the unvaccinated group (OR 0.35; 95% CI 0.21–0.56; p < 0.0001). The recurrence of CIN 1+ after treatment was significantly lower in the vaccinated compared with the unvaccinated group (OR 0.51; 95% CI 0.31–0.83; p = 0.006). A non-significant trend of reduction rate of HPV persistence was observed in the vaccinated compared with the unvaccinated cohorts (OR was 0.84; 95% CI 0.61–1.15; p = 0.28). Conclusions: HPV vaccination, in adjuvant setting, is associated with a reduced risk of recurrent CIN 1+ and CIN 2+ after surgical treatment.

The objective of this work is to assess the 5-year outcomes of patients undergoing conization for high-grade cervical lesions that simultaneously present as risk factors in the persistence of HPV infection and the positivity of surgical resection margins. This is a retrospective study evaluating patients undergoing conization for high-grade cervical lesions. All patients included had both positive surgical margins and experienced HPV persistence at 6 months. Associations were evaluated with Cox proportional hazard regression and summarized using hazard ratio (HR). The charts of 2966 patients undergoing conization were reviewed. Among the whole population, 163 (5.5%) patients met the inclusion criteria, being at high risk due to the presence of positive surgical margins and experiencing HPV persistence. Of 163 patients included, 17 (10.4%) patients developed a CIN2+ recurrence during the 5-year follow-up. Via univariate analyses, diagnosis of CIN3 instead of CIN2 (HR: 4.88 (95%CI: 1.10, 12.41); p = 0.035) and positive endocervical instead of ectocervical margins (HR: 6.44 (95%CI: 2.80, 9.65); p < 0.001) were associated with increased risk of persistence/recurrence. Via multivariate analyses, only positive endocervical instead of ectocervical margins (HR: 4.56 (95%CI: 1.23, 7.95); p = 0.021) were associated with worse outcomes. In this high-risk group, positive endocervical margins is the main risk factor predicting 5-year recurrence.

Endometriosis is a condition characterized by the presence of endometrial tissue outside the uterine cavity, leading to a chronic inflammatory reaction. It is one of the most widespread gynecological diseases with a 10–15% prevalence in the general female population, rising up to 30–45% in patients with infertility. Although it was first described in 1860, its etiology and pathogenesis are still unclear. It is now accepted that inflammation plays a central role in the development and progression of endometriosis. In particular, it is marked by an inflammatory process associated with the overproduction of an array of inflammatory mediators such as prostaglandins, metalloproteinases, cytokines, and chemokines. In addition, the growth and adhesion of endometrial cells in the peritoneal cavity due to reactive oxygen species (ROS) and free radicals lead to disease onset, its ensuing symptoms—among which pain and infertility. The aim of our review is to evaluate the role of oxidative stress and ROS in the pathogenesis of endometriosis and the efficacy of antioxidant therapy in the treatment and mitigation of its symptoms.

Background: Cervical dysplasia persistence/recurrence has a great impact on women’s health and quality of life. In this study, we investigated whether a prognostic nomogram may improve risk assessment after primary conization. Methods: This is a retrospective multi-institutional study based on charts of consecutive patients undergoing conization between 1 January 2010 and 31 December 2014. A nomogram assessing the importance of different variables was built. A cohort of patients treated between 1 January 2015 and 30 June 2016 was used to validate the nomogram. Results: A total of 2966 patients undergoing primary conization were analyzed. The median (range) patient age was 40 (18–89) years. At 5-year of follow-up, 6% of patients (175/2966) had developed a persistent/recurrent cervical dysplasia. Median (range) recurrence-free survival was 18 (5–52) months. Diagnosis of CIN3, presence of HR-HPV types, positive endocervical margins, HPV persistence, and the omission of HPV vaccination after conization increased significantly and independently of the risk of developing cervical dysplasia persistence/recurrence. A nomogram weighting the impact of all variables was built with a C-Index of 0.809. A dataset of 549 patients was used to validate the nomogram, with a C-index of 0.809. Conclusions: The present nomogram represents a useful tool for counseling women about their risk of persistence/recurrence after primary conization. HPV vaccination after conization is associated with a reduced risk of CIN2+.

Ovarian cancer (OC) is the eighth most common cancer in women. Since screening programs do not exist, it is often diagnosed in advanced stages. Today, the detection of OC is based on clinical examination, transvaginal ultrasound (US), and serum biomarker (Carbohydrate Antigen 125 (CA 125) and Human Epididymis Protein 4 (HE4)) dosage, with a sensitivity of 88% and 95%, respectively, and a specificity of 84% for US and 76% for biomarkers. These methods are clearly not enough, and OC in its early stages is often missed. Many scientists have recently focused their attention on volatile organic compounds (VOCs). These are gaseous molecules, found in the breath, that could provide interesting information on several diseases, including solid tumors. To detect VOCs, an electronic nose was invented by a group of researchers. A similar device, the e-tongue, was later created to detect specific molecules in liquids. For the first time in the literature, we investigated the potential use of the electronic nose and the electronic tongue to detect ovarian cancer not just from breath but also from urine, blood, and plasma samples.