Feedforward networks in financial predictions: the future that modifies the present

The main goal of this paper is to show how relatively minor modifications of well-known algorithms (in particular, back propagation) can dramatically increase the performance of an artificial neural network (ANN) for time series prediction. We denote our proposed sets of modifications as the 'self-momentum', 'Freud' and 'Jung' rules. In our opinion, they provide an example of an alternative approach to the design of learning strategies for ANNs, one that focuses on basic mathematical conceptualization rather than on formalism and demonstration. The complexity of actual prediction problems makes it necessary to experiment with modelling possibilities whose inherent mathematical properties are often not well understood yet. The problem of time series prediction in stock markets is a case in point. It is well known that asset price dynamics in financial markets are difficult to trace, let alone to predict with an operationally interesting degree of accuracy. We therefore take financial prediction as a meaningful test bed for the validation of our techniques. We discuss in some detail both the theoretical underpinnings of the technique and our case study about financial prediction, finding encouraging evidence that supports the theoretical and operational viability of our new ANN specifications. Ours is clearly only a preliminary step. Further developments of ANN architectures with more and more sophisticated 'learning to learn' characteristics are now under study and test.     

Multimodal support to group dynamics

The complexity of group dynamics occurring in small group interactions often hinders the performance of teams. The availability of rich multimodal information about what is going on during the meeting makes it possible to explore the possibility of providing support to dysfunctional teams from facilitation to training sessions addressing both the individuals and the group as a whole. A necessary step in this direction is that of capturing and understanding group dynamics. In this paper, we discuss a particular scenario, in which meeting participants receive multimedia feedback on their relational behaviour, as a first step towards increasing self-awareness. We describe the background and the motivation for a coding scheme for annotating meeting recordings partially inspired by the Bales’ Interaction Process Analysis. This coding scheme was aimed at identifying suitable observable behavioural sequences. The study is complemented with an experimental investigation on the acceptability of such a service.

---

Segmentation of news videos based on audio-video information

In this paper, we propose an innovative architecture to segment a news video into the so-called “stories” by both using the included video and audio information. Segmentation of news into stories is one of the key issues for achieving efficient treatment of news-based digital libraries. While the relevance of this research problem is widely recognized in the scientific community, we are in presence of a few established solutions in the field. In our approach, the segmentation is performed in two steps: first, shots are classified by combining three different anchor shot detection algorithms using video information only. Then, the shot classification is improved by using a novel anchor shot detection method based on features extracted from the audio track. Tests on a large database confirm that the proposed system outperforms each single video-based method as well as their combination.

The Beginning of Meiosis in Mammalian Female Germ Cells: A Never-Ending Story of Intrinsic and Extrinsic Factors

Meiosis is the unique division of germ cells resulting in the recombination of the maternal and paternal genomes and the production of haploid gametes. In mammals, it begins during the fetal life in females and during puberty in males. In both cases, entering meiosis requires a timely switch from the mitotic to the meiotic cell cycle and the transition from a potential pluripotent status to meiotic differentiation. Revealing the molecular mechanisms underlying these interrelated processes represents the essence in understanding the beginning of meiosis. Meiosis facilitates diversity across individuals and acts as a fundamental driver of evolution. Major differences between sexes and among species complicate the understanding of how meiosis begins. Basic meiotic research is further hindered by a current lack of meiotic cell lines. This has been recently partly overcome with the use of primordial-germ-cell-like cells (PGCLCs) generated from pluripotent stem cells. Much of what we know about this process depends on data from model organisms, namely, the mouse; in mice, the process, however, appears to differ in many aspects from that in humans. Identifying the mechanisms and molecules controlling germ cells to enter meiosis has represented and still represents a major challenge for reproductive medicine. In fact, the proper execution of meiosis is essential for fertility, for maintaining the integrity of the genome, and for ensuring the normal development of the offspring. The main clinical consequences of meiotic defects are infertility and, probably, increased susceptibility to some types of germ-cell tumors. In the present work, we report and discuss data mainly concerning the beginning of meiosis in mammalian female germ cells, referring to such process in males only when pertinent. After a brief account of this process in mice and humans and an historical chronicle of the major hypotheses and progress in this topic, the most recent results are reviewed and discussed.     

PET-Derived Radiomics and Artificial Intelligence in Breast Cancer: A Systematic Review

Breast cancer (BC) is a heterogeneous malignancy that still represents the second cause of cancer-related death among women worldwide. Due to the heterogeneity of BC, the correct identification of valuable biomarkers able to predict tumor biology and the best treatment approaches are still far from clear. Although molecular imaging with positron emission tomography/computed tomography (PET/CT) has improved the characterization of BC, these methods are not free from drawbacks. In recent years, radiomics and artificial intelligence (AI) have been playing an important role in the detection of several features normally unseen by the human eye in medical images. The present review provides a summary of the current status of radiomics and AI in different clinical settings of BC. A systematic search of PubMed, Web of Science and Scopus was conducted, including all articles published in English that explored radiomics and AI analyses of PET/CT images in BC. Several studies have demonstrated the potential role of such new features for the staging and prognosis as well as the assessment of biological characteristics. Radiomics and AI features appear to be promising in different clinical settings of BC, although larger prospective trials are needed to confirm and to standardize this evidence.     

TRPML2 Mucolipin Channels Drive the Response of Glioma Stem Cells to Temozolomide and Affect the Overall Survival in Glioblastoma Patients

The survival of patients with glioblastoma (GBM) is poor. The main cause is the presence of glioma stem cells (GSCs), exceptionally resistant to temozolomide (TMZ) treatment. This last may be related to the heterogeneous expression of ion channels, among them TRPML2. Its mRNA expression was evaluated in two different neural stem cell (NS/PC) lines and sixteen GBM stem-like cells by qRT-PCR. The response to TMZ was evaluated in undifferentiated or differentiated GSCs, and in TRPML2-induced or silenced GSCs. The relationship between TRPML2 expression and responsiveness to TMZ treatment was evaluated by MTT assay showing that increased TRPML2 mRNA levels are associated with resistance to TMZ. This research was deepened by qRT-PCR and western blot analysis. PI3K/AKT and JAK/STAT pathways as well as ABC and SLC drug transporters were involved. Finally, the relationship between TRPML2 expression and overall survival (OS) and progression-free survival (PFS) in patient-derived GSCs was evaluated by Kaplan–Meier analysis. The expression of TRPML2 mRNA correlates with worse OS and PFS in GBM patients. Thus, the expression of TRPML2 in GSCs influences the responsiveness to TMZ in vitro and affects OS and PFS in GBM patients.     

Efficient breadth first search on multi-GPU systems

Simple algorithms for the execution of a Breadth First Search on large graphs lead, running on clusters of GPUs, to a situation of load unbalance among threads and un-coalesced memory accesses, resulting in pretty low performances. To obtain a significant improvement on a single GPU and to scale by using multiple GPUs, we resort to a suitable combination of operations to rearrange data before processing them. We propose a novel technique for mapping threads to data that achieves a perfect load balance by leveraging prefix-sum and binary search operations. To reduce the communication overhead, we perform a pruning operation on the set of edges that needs to be exchanged at each BFS level. The result is an algorithm that exploits at its best the parallelism available on a single GPU and minimizes communication among GPUs. We show that a cluster of GPUs can efficiently perform a distributed BFS on graphs with billions of nodes.     

Polymer Encapsulated Liposomes for Oral Co-Delivery of Curcumin and Hydroxytyrosol

Curcumin (Cur) is a hydrophobic polyphenol from the rhizome of Curcuma spp., while hydroxytyrosol (HT) is a water-soluble polyphenol from Olea europaea. Both show outstanding antioxidant properties but suffer from scarce bioavailability and low stability in biological fluids. In this work, the co-encapsulation of Cur and HT into liposomes was realized, and the liposomal formulation was improved using polymers to increase their survival in the gastrointestinal tract. Liposomes with different compositions were formulated: Type 1, composed of phospholipids and cholesterol; Type 2, also with a PEG coating; and Type 3 providing an additional shell of Eudragit^® S100, a gastro-resistant polymer. Samples were characterized in terms of size, morphology, ζ-potential, encapsulation efficiency, and loading capacity. All samples were subjected to a simulated in vitro digestion and their stability was investigated. The Eudragit^®S100 coating demonstrated prevention of early releases of HT in the mouth and gastric phases, while the PEG shell reduced bile salts and pancreatin effects during the intestinal digestion. In vitro antioxidant activity showed a cumulative effect for Cur and HT loaded in vesicles. Finally, liposomes with HT concentrations up to 40 μM and Cur up to 4.7 μM, alone or in combination, did not show cytotoxicity against Caco-2 cells.     

Clinical Significance of Molecular Subtypes in Western Advanced Gastric Cancer: A Real-World Multicenter Experience

In recent years, the molecular subtyping of gastric cancer has led to the identification of novel clinically relevant biomarkers as well as promising therapeutic targets. In parallel, the advent of checkpoint inhibitors has expanded treatment options beyond conventional chemotherapy. Compelling evidence has shown unprecedented efficacy results for anti-PD1-based therapies in the molecular subgroups of dMMR/MSI-h, EBV+ and PD-L1 CPS+ patients, to the point that these are granted approval for gastric cancer adenocarcinoma (AGC) in several countries. Despite this, cytotoxic chemotherapy remains the only treatment choice for the considerable proportion of biomarkers-negative patients. In this context, little is known about the association between subtypes-defining biomarkers (HER2, MMR/MSI, PD-L1, and EBV) and the efficacy of standard chemotherapy in non-Asian AGC. Here, we aimed to investigate the prevalence, the clinic-pathologic features, and the impact on treatment outcome of clinical molecular subtypes in a new-diagnosed Western cohort of AGC.